© 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. 19-RESID-POST-AA
    11. 70554
    Prev
    Next
    INDEX
    Explanations

    say positive adjectives

    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
     prescriptions
    -0.09
    acing
    -0.07
    organizations
    -0.07
    .asarray
    -0.06
     paddingLeft
    -0.06
    pgsql
    -0.06
     sag
    -0.06
    .tile
    -0.06
    أن
    -0.06
    ReadOnly
    -0.06
    POSITIVE LOGITS
    ellipsis
    0.08
     huyện
    0.07
    メリット
    0.07
    _probs
    0.07
    _xt
    0.07
     Ağustos
    0.07
    .counter
    0.07
    🚚
    0.07
     Megan
    0.07
     MV
    0.07
    Activations Density 0.267%

    No Known Activations