© 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. 19-RESID-POST-AA
    11. 1972
    Prev
    Next
    INDEX
    Explanations

    elbow

    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_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     deficits
    -0.07
    שו
    -0.07
    jee
    -0.07
    在京
    -0.06
    娠
    -0.06
     Assessment
    -0.06
    测
    -0.06
    <lemma
    -0.06
     область
    -0.06
    testdata
    -0.06
    POSITIVE LOGITS
     elegant
    0.08
     RPM
    0.08
    opping
    0.07
    _WORK
    0.07
    ULA
    0.07
     permalink
    0.07
    agento
    0.07
    WR
    0.07
    hões
    0.07
     MPH
    0.07
    Activations Density 0.005%

    No Known Activations