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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 23-RESID-POST-AA
    11. 1110
    Prev
    Next
    INDEX
    Explanations

    say "the ending -ing"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_23/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Bluetooth
    -0.06
    HTTPRequest
    -0.06
    obsolete
    -0.06
    כיר
    -0.06
    MET
    -0.06
    却是
    -0.06
     그런데
    -0.06
    却被
    -0.06
    הב
    -0.06
    alo
    -0.06
    POSITIVE LOGITS
    ;i
    0.07
    Ἱ
    0.07
    省教育
    0.07
    /";↵↵
    0.07
    waves
    0.06
    腱
    0.06
    <dim
    0.06
     bền
    0.06
    ⴼ
    0.06
     товаров
    0.06
    Activations Density 0.048%

    No Known Activations