© 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. 19782
    Prev
    Next
    INDEX
    Explanations

    counts of crimes

    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
    èĮ¬
    -0.10
    ä¸ĢäºĽ
    -0.09
    è¿Ļåľº
    -0.08
    å°±æĪIJäºĨ
    -0.08
    åIJ¬è¿ĩ
    -0.08
    ä¸įæħİ
    -0.08
    ä¸ĭåįĬåľº
    -0.08
    edu
    -0.08
    case
    -0.08
    å¾ģ
    -0.08
    POSITIVE LOGITS
    isce
    0.10
    ãģ¤ãģĭ
    0.09
    éļĻ
    0.09
    ä¼ĹæīĢ
    0.08
    icom
    0.08
    ksen
    0.08
    ç°§
    0.08
     favourites
    0.08
    ixo
    0.08
    åİŁæłĩé¢ĺ
    0.08
    Activations Density 0.026%

    No Known Activations