© 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. 4850
    Prev
    Next
    INDEX
    Explanations

    -playing

    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
     blankets
    -0.07
     dark
    -0.07
    总会
    -0.07
    .setX
    -0.07
    dıklar
    -0.07
     Succ
    -0.07
    夬
    -0.07
     ella
    -0.07
     rfl
    -0.07
     הספר
    -0.07
    POSITIVE LOGITS
    .Description
    0.07
    -rounded
    0.06
     VER
    0.06
    .task
    0.06
     Isaiah
    0.06
    賓
    0.06
     Nevertheless
    0.06
    轩
    0.06
    amed
    0.06
    ╏
    0.06
    Activations Density 0.002%

    No Known Activations