© 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. 19744
    Prev
    Next
    INDEX
    Explanations

    Inca Trail

    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
    bor
    -0.09
    éĥ½è§īå¾Ĺ
    -0.09
    ucs
    -0.09
    eda
    -0.08
    /qt
    -0.08
    ÑĢÑĭ
    -0.08
    BOR
    -0.08
    æ¸İ
    -0.08
    åįļè§Ī
    -0.08
    elly
    -0.08
    POSITIVE LOGITS
     ÙħØŃÙħ
    0.09
    ipse
    0.09
    idad
    0.09
    山寨
    0.08
     springs
    0.08
    ç»ĵ
    0.08
    htag
    0.08
    寨
    0.08
    mania
    0.08
    gettext
    0.08
    Activations Density 0.003%

    No Known Activations