© 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. 62729
    Prev
    Next
    INDEX
    Explanations

    essays and research papers

    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
    让æĤ¨
    -0.08
    å¼Ń
    -0.08
    ç»´
    -0.08
    éĢł
    -0.08
    岫
    -0.08
    éĵ²
    -0.07
     Dept
    -0.07
    西æ´ĭ
    -0.07
    家éŨåı£
    -0.07
     cookbook
    -0.07
    POSITIVE LOGITS
    èĮĥæĸĩ
    0.13
    åĨĻä½ľ
    0.12
    Essay
    0.11
    yth
    0.09
    åħīéĺ´
    0.09
    MUX
    0.09
    paralle
    0.09
    .lt
    0.09
    è¿¢
    0.09
    .Argument
    0.09
    Activations Density 0.122%

    No Known Activations