© 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. 30072
    Prev
    Next
    INDEX
    Explanations

    distribute under certain terms

    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
    åIJĮèĥŀ
    -0.09
    é¾Ł
    -0.09
    é£İéĩĩ
    -0.09
    æĥ¨
    -0.09
    éĶIJ
    -0.09
    ä¸Ńæĸĩ
    -0.08
    _FN
    -0.08
    模èĮĥ
    -0.08
    åĬŁå¤«
    -0.08
    çĶ¨æĪ·æıIJä¾Ľ
    -0.08
    POSITIVE LOGITS
    ç»Ļ人
    0.09
    æµĨ
    0.09
    å²Ķ
    0.08
    tar
    0.08
    ãģĬ
    0.08
    åĬ¼
    0.08
    ä¸ĭçıŃ
    0.08
    宣æī¬
    0.08
     Bulk
    0.08
    èĸª
    0.08
    Activations Density 0.112%

    No Known Activations