© 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. 33688
    Prev
    Next
    INDEX
    Explanations

    transport traits

    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
    ideon
    -0.09
    vide
    -0.09
     kè
    -0.09
    æ¼Ĥæµģ
    -0.08
    æ¼Ĥ
    -0.08
    ipse
    -0.08
     rude
    -0.08
    ç«ĭ足
    -0.08
    潮湿
    -0.08
    åįļ主
    -0.08
    POSITIVE LOGITS
    导读
    0.11
    è¿ŀè½½
    0.10
    éĢļ
    0.09
    ç¦Ħ
    0.09
    è¿IJè¾ĵ
    0.09
    íĨµ
    0.09
    è¾ĵ
    0.09
    _EMPTY
    0.09
    åºĹåĨħ
    0.09
    巨人
    0.09
    Activations Density 0.179%

    No Known Activations