© 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. 35710
    Prev
    Next
    INDEX
    Explanations

    a member of

    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
    ÄĤ
    -0.09
    ilver
    -0.09
    éŃģ
    -0.08
    åĬ©
    -0.08
    elden
    -0.08
    н
    -0.08
    ä¸Ģ段
    -0.08
     Vig
    -0.08
    åĸĦæĦı
    -0.08
    åĮı
    -0.08
    POSITIVE LOGITS
    ä¸įåłª
    0.09
    éĻ©
    0.09
     plateau
    0.09
    ç»ĵæĿŁäºĨ
    0.08
    è±ģ
    0.08
    迤
    0.08
    ãĥ¡ãĥ³ãĥĪ
    0.08
    uded
    0.08
    åĽ½æ°ij
    0.08
    åģİ
    0.08
    Activations Density 0.134%

    No Known Activations