© 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. 17886
    Prev
    Next
    INDEX
    Explanations

    of mathematical equations

    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
    åı¯ä»¥èİ·å¾Ĺ
    -0.10
    åĽĬ
    -0.10
    éļħ
    -0.09
    éĢļæĬ¥
    -0.08
    ä¸Ģç¬Ķ
    -0.08
    éĴŁ
    -0.08
    å·¥ç¨ĭæĬĢæľ¯
    -0.08
    æĻŀ
    -0.08
    åķľ
    -0.07
    åıĺå¾ĹæĽ´
    -0.07
    POSITIVE LOGITS
    èĩ³äºİ
    0.10
    chine
    0.09
    è°ĥåĬ¨
    0.09
    è°¬
    0.08
    _Str
    0.08
    濯
    0.08
    å°ıç»Ħ
    0.08
    ÑĥÑħ
    0.08
    使
    0.08
    ä¸įçĶ¨
    0.08
    Activations Density 0.853%

    No Known Activations