© 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. 71125
    Prev
    Next
    INDEX
    Explanations

    For

    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
     horizontal
    -0.08
    (Direction
    -0.07
    .readyState
    -0.07
     nghiên
    -0.07
     upd
    -0.07
     remaining
    -0.07
    就好了
    -0.07
    码
    -0.07
    ouver
    -0.06
     móc
    -0.06
    POSITIVE LOGITS
     xhttp
    0.07
    пат
    0.07
     oats
    0.07
    蒽
    0.07
    _environment
    0.07
     sólo
    0.07
    .Interface
    0.07
    'label
    0.06
     Cynthia
    0.06
     kvinne
    0.06
    Activations Density 0.019%

    No Known Activations