© 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. 35500
    Prev
    Next
    INDEX
    Explanations

    // Copyright, wi-fi

    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
    BOSE
    -0.10
    åĨįéĢł
    -0.09
    .scal
    -0.09
    为æѤ
    -0.09
    errat
    -0.09
    .shtml
    -0.09
    æ»ļçIJĥ
    -0.09
    artin
    -0.09
     Kore
    -0.09
    åIJĵå¾Ĺ
    -0.09
    POSITIVE LOGITS
    é¦į
    0.09
    å¤ĸå¢Ļ
    0.09
    è°Ł
    0.09
    åĴĮæĶ¯æĮģ
    0.08
    æĬ¥åijĬæľŁåĨħ
    0.08
    ISCO
    0.08
    æĥ®
    0.08
    èįIJ
    0.08
    éĢļå¾Ģ
    0.08
    æµģ产
    0.08
    Activations Density 0.036%

    No Known Activations