© 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. 58973
    Prev
    Next
    INDEX
    Explanations

    Copyright year

    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
     Covered
    -0.08
    .stamp
    -0.08
    ä»ĸæĽ¾
    -0.08
    çªĸ
    -0.08
    çī¹æ´¾
    -0.08
     tela
    -0.08
    icons
    -0.08
    ìľĦìĽIJ
    -0.08
    ä¹ŁåIJĮæł·
    -0.07
    æľĪä¸ĭ
    -0.07
    POSITIVE LOGITS
    ONES
    0.09
    éĿ¢ç§¯çº¦
    0.08
    hare
    0.08
    å¿ĥæĥħ
    0.08
     itemView
    0.08
    ä¸ĢéĿ¢
    0.08
    ALLE
    0.08
    èķ¨
    0.08
    eof
    0.08
    ä¸įé«ĺ
    0.08
    Activations Density 0.309%

    No Known Activations