© 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. 49749
    Prev
    Next
    INDEX
    Explanations

    quotes followed by words indicating consequences or continuations

    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
    eded
    -0.09
    [
    -0.08
    ä»ħä¾Ľ
    -0.08
    åķ·
    -0.08
    kip
    -0.08
    erna
    -0.08
    æĸ°è¥¿
    -0.08
    çľ¼çļ®
    -0.07
     ‘
    -0.07
    .net
    -0.07
    POSITIVE LOGITS
    .fromCharCode
    0.09
     воÑĤ
    0.09
    ÑģÑģ
    0.09
    å¤ļä½Ļ
    0.09
     tym
    0.09
    combe
    0.09
    _Impl
    0.09
    ielding
    0.09
    GINE
    0.08
    è¡¡éĺ³
    0.08
    Activations Density 0.070%

    No Known Activations