© 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. 4715
    Prev
    Next
    INDEX
    Explanations

    hymn

    np_max-act · gemini-2.0-flash
    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
     уд
    -0.06
    狐月山
    -0.06
    uly
    -0.06
     David
    -0.06
    Cached
    -0.06
     Sant
    -0.06
     BUILD
    -0.06
    ᠆
    -0.06
    _SQL
    -0.06
     []
    -0.06
    POSITIVE LOGITS
    wüns
    0.08
    printing
    0.07
    employed
    0.07
    dense
    0.07
    чист
    0.07
    .event
    0.07
     enrollment
    0.07
    sexual
    0.07
    𧿹
    0.07
    mojom
    0.07
    Activations Density 0.002%

    No Known Activations