© 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. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 6455
    Prev
    Next
    INDEX
    Explanations

    distinctly affected or different

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    帷
    -0.09
    éĿĻéĿĻ
    -0.08
    èĦ±
    -0.08
    /small
    -0.08
    åĪ»
    -0.08
    ues
    -0.08
    kills
    -0.08
    agged
    -0.08
     Tee
    -0.07
    满
    -0.07
    POSITIVE LOGITS
    å°Ŀ
    0.10
    stile
    0.09
    å¤ļãģı
    0.09
    åı¦ä¸Ģ
    0.09
    ä¸įèĪĴæľį
    0.09
    å¤ļãģĦ
    0.09
     decidedly
    0.09
    ively
    0.09
     ê·¸ëłĩì§Ģ
    0.09
    ä¸įåĪ©äºİ
    0.09
    Activations Density 0.023%

    No Known Activations