© 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. 54449
    Prev
    Next
    INDEX
    Explanations

    witty essay

    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
    æIJŀå¾Ĺ
    -0.09
     appe
    -0.09
    .streaming
    -0.08
     unarmed
    -0.08
    èħ¿
    -0.08
    åľ¨äº¬
    -0.08
    è¢ĸ
    -0.08
    vide
    -0.08
    ESC
    -0.08
    ä¸įæ¸ħ
    -0.08
    POSITIVE LOGITS
    éªĪ
    0.11
    读èĢħ
    0.11
    éĥ¨ç½²
    0.10
    åĨĻä½ľ
    0.10
    æĸĩä½ĵ
    0.10
    åı¥åŃIJ
    0.10
    è¡Įç¨ĭ
    0.09
    æķ£
    0.09
    éĢļæĬ¥
    0.09
    æııåĨĻ
    0.09
    Activations Density 0.047%

    No Known Activations