© 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. 7627
    Prev
    Next
    INDEX
    Explanations

    @Table, Table

    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
    早早
    -0.08
    收拾
    -0.07
     SD
    -0.07
    颛
    -0.07
    TreeWidgetItem
    -0.07
     Sega
    -0.07
    迪士
    -0.07
    appropriate
    -0.07
    谟
    -0.07
    خذ
    -0.07
    POSITIVE LOGITS
     tokenizer
    0.07
     pollut
    0.07
    Word
    0.06
     )"
    0.06
     '?
    0.06
     truncated
    0.06
    -dominated
    0.06
    /antlr
    0.06
    的主题
    0.06
     Exec
    0.06
    Activations Density 0.001%

    No Known Activations