© 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. 118915
    Prev
    Next
    INDEX
    Explanations

    Portuguese/Spanish

    np_max-act · gemini-2.0-flash
    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
     verschied
    -0.09
    registr
    -0.09
    变身
    -0.08
    狩
    -0.08
    找了
    -0.08
    前身
    -0.08
    مرض
    -0.08
    打了
    -0.07
    离
    -0.07
    ']."</
    -0.07
    POSITIVE LOGITS
    但是他
    0.12
    所以他
    0.10
    也希望
    0.09
    也是很
    0.09
    被誉
    0.08
    缛
    0.08
    '].'</
    0.08
    所以我
    0.08
    ,"%
    0.08
    を作る
    0.08
    Activations Density 2.205%

    No Known Activations