© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 15-RESID-POST-AA
    11. 29817
    Prev
    Next
    INDEX
    Explanations

    articles/prepositions

    np_max-act · gemini-2.0-flash

    definite articles and other high-frequency function words, often appearing at the beginnings of sentences or noun phrases.

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     chapter
    -0.07
    ച
    -0.07
    permalink
    -0.07
    有一些
    -0.07
    ($('<
    -0.07
    浦
    -0.06
    uant
    -0.06
     Tiểu
    -0.06
     submitting
    -0.06
    蘧
    -0.06
    POSITIVE LOGITS
    Orig
    0.08
    ⁉
    0.07
    ♬
    0.07
     نهائي
    0.07
    ERV
    0.07
    EXT
    0.06
    Reporting
    0.06
    _NAV
    0.06
     Welt
    0.06
    DEVICE
    0.06
    Activations Density 1.238%

    No Known Activations