© 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. 9944
    Prev
    Next
    INDEX
    Explanations

    Alexa Rank

    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
    è¿ŁåĪ°
    -0.09
    æĪij们ä¸Ģèµ·
    -0.09
    éĥ½è§īå¾Ĺ
    -0.09
    ç¨ĭ
    -0.08
    å¾ķ
    -0.08
    å¥ı
    -0.08
    书ä¸Ń
    -0.08
     Rat
    -0.08
     runaway
    -0.08
     Incredible
    -0.08
    POSITIVE LOGITS
    çĶŁåij½åĬĽ
    0.10
    ä¸ĸçķĮä¸Ģæµģ
    0.10
    åľ°ä½į
    0.09
    çīł
    0.09
    yar
    0.08
     sla
    0.08
    çŁ¥åIJį度
    0.08
     znal
    0.08
    åĪĪ
    0.08
    .appspot
    0.08
    Activations Density 0.044%

    No Known Activations