© 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. 55662
    Prev
    Next
    INDEX
    Explanations

    have it

    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
    æ¡¢
    -0.09
    avar
    -0.09
    è¿Ľåħ¥äºĨ
    -0.09
    åIJ¸çº³
    -0.08
    èĢĮä¸Ķ
    -0.08
    绣çŃ¹æİ¨è¿Ľ
    -0.08
     Scha
    -0.08
    appings
    -0.08
    æĬ¥èĢĥ
    -0.08
    麦
    -0.08
    POSITIVE LOGITS
    erals
    0.09
    ä¸įåĪĨ
    0.09
    heim
    0.09
    Ñıн
    0.09
    .assertj
    0.09
    iego
    0.09
    ç»
    0.08
    è´±
    0.08
    undy
    0.08
    ODO
    0.08
    Activations Density 0.043%

    No Known Activations