© 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. 61481
    Prev
    Next
    INDEX
    Explanations

    good or well followed by context

    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
    æĸ°æĪ¿
    -0.10
    æĪĸæĺ¯
    -0.08
    é¢ł
    -0.08
    éĻ¢éĻ¢å£«
    -0.08
     anomal
    -0.08
    ç®Ń
    -0.08
    çĮĸ
    -0.08
     Polar
    -0.08
     aggrav
    -0.08
    Tesla
    -0.07
    POSITIVE LOGITS
    ember
    0.09
    icap
    0.09
    oped
    0.09
    å°±å¤Ł
    0.08
    å·¥åķĨ
    0.08
    åįķ项
    0.08
    oto
    0.08
    æ¥Ķ
    0.08
    ä¸įåIJĮç¨ĭ度
    0.08
    quine
    0.08
    Activations Density 0.187%

    No Known Activations