© 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. 61937
    Prev
    Next
    INDEX
    Explanations

    any, all, every, whatever, various

    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
    ESIS
    -0.09
    sworth
    -0.09
    åĬ¨å·¥
    -0.09
    åľĪ
    -0.09
    æĹ¥æĬ¥è®°èĢħ
    -0.09
    oretical
    -0.08
    _SA
    -0.08
     jean
    -0.08
    ç¦ıéŁ³
    -0.08
    è¿Ļç§įæĸ¹æ³ķ
    -0.08
    POSITIVE LOGITS
    oning
    0.09
    å¹´é¾Ħ段
    0.09
    åħħæĸ¥
    0.09
    mo
    0.09
     Wax
    0.08
    æŶåĢĻ
    0.08
    vik
    0.08
    æĢİ
    0.08
    æ»´æ»´
    0.08
    è··
    0.08
    Activations Density 0.034%

    No Known Activations