© 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. 64106
    Prev
    Next
    INDEX
    Explanations

    questions directly addressing the assistant about its identity, abilities, behavior, or comparisons to other AI models.

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    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
     forthcoming
    -0.07
     CommonModule
    -0.07
    thed
    -0.07
    救灾
    -0.07
    imeo
    -0.07
    eny
    -0.06
    Deg
    -0.06
    淹没
    -0.06
    uyết
    -0.06
     arrests
    -0.06
    POSITIVE LOGITS
    quisar
    0.07
     Royale
    0.07
     SF
    0.06
    Kill
    0.06
    -setup
    0.06
     Nz
    0.06
     ()↵
    0.06
    .easy
    0.06
    abwe
    0.06
    Ab
    0.06
    Activations Density 0.155%

    No Known Activations