© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 37907
    Prev
    Next
    INDEX
    Explanations

    path separators and following numbers

    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
    -0.09
    dom
    -0.09
    æĪĸå¤ļ
    -0.09
    umat
    -0.09
    .Inner
    -0.08
    lets
    -0.08
    Rated
    -0.08
    åĩłçĤ¹
    -0.08
     nuts
    -0.08
    pack
    -0.08
    POSITIVE LOGITS
    vor
    0.10
    ç½Ħ
    0.09
    ä¸įåIJĮç¨ĭ度
    0.08
    åķ¬
    0.08
    _strike
    0.08
    ptest
    0.08
    人æµģ
    0.08
    ä¸Ģåįĥ
    0.08
    æĥ®
    0.08
     cairo
    0.08
    Activations Density 0.004%

    No Known Activations