© 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. 30205
    Prev
    Next
    INDEX
    Explanations

    passed on

    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
    è¨ĩ
    -0.10
    åŁł
    -0.09
    ä¸īæĿ¡
    -0.09
    ãģ¨ãģĦãģ£ãģ¦
    -0.09
    emia
    -0.09
    orts
    -0.09
    -pill
    -0.09
    ensibly
    -0.09
    çļĦèĥĮåIJİ
    -0.09
    ä¸¤å¼ł
    -0.08
    POSITIVE LOGITS
    ä¼łéĢĴ
    0.10
    ä¸Ģ身
    0.09
    çĤĻ
    0.09
    çĽ¸ä¼ł
    0.09
    _TRANSFER
    0.08
    ä¸ĭæĿ¥çļĦ
    0.08
     Gol
    0.08
    èĪ±
    0.08
     agre
    0.08
    utan
    0.07
    Activations Density 0.041%

    No Known Activations