© 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. 56059
    Prev
    Next
    INDEX
    Explanations

    each day/days

    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
    ä¸Ńç§ĭ
    -0.09
    çİ©
    -0.08
    ouple
    -0.08
     asc
    -0.08
    ISTER
    -0.08
    åĻİ
    -0.08
     eventual
    -0.08
    xCC
    -0.08
    Ùģاء
    -0.08
     Claus
    -0.07
    POSITIVE LOGITS
    æ¯ıæĹ¥
    0.13
    æ¯ıä¸Ģ天
    0.12
    æ¯ı天éĥ½
    0.12
    éĨĴæĿ¥
    0.11
    çļĦå¿ĥæĥħ
    0.11
    åīįä¸Ģ天
    0.10
    éĨĴ
    0.10
    æ¯ı天
    0.10
    yal
    0.10
    éĴī
    0.10
    Activations Density 0.034%

    No Known Activations