© 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. 70874
    Prev
    Next
    INDEX
    Explanations

    removing traces of software

    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
     basil
    -0.08
    oro
    -0.07
    herited
    -0.06
    bas
    -0.06
     principalTable
    -0.06
     behaviors
    -0.06
     vitality
    -0.06
     بص
    -0.06
     shortcuts
    -0.06
    .species
    -0.06
    POSITIVE LOGITS
    עונ
    0.07
    .load
    0.07
    mma
    0.07
    د
    0.07
    驳
    0.07
    \Client
    0.07
    _od
    0.07
     lớp
    0.07
     Finger
    0.07
    $order
    0.07
    Activations Density 0.005%

    No Known Activations