© 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. 62908
    Prev
    Next
    INDEX
    Explanations

    what following

    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
    ä¸Ģ大
    -0.09
    lasses
    -0.08
    åĽŀäºĭ
    -0.08
    rement
    -0.07
    åľĪ
    -0.07
    .Act
    -0.07
     Clair
    -0.07
    ä¸įè´Ł
    -0.07
    æ¼ł
    -0.07
    ugin
    -0.07
    POSITIVE LOGITS
    æģ½
    0.10
    PropertyParams
    0.10
    -layout
    0.10
    åī©ä¸ĭ
    0.09
    _CAST
    0.09
    缺失
    0.09
    æĥĬåı¹
    0.09
    Ø·Ùģ
    0.09
    åģıåģı
    0.09
    èijº
    0.09
    Activations Density 0.039%

    No Known Activations