© 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. 38939
    Prev
    Next
    INDEX
    Explanations

    Evil Dead Red

    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
    [email
    -0.08
    è¿Ļ两ç§į
    -0.08
    _bootstrap
    -0.08
    æ¸ĹéĢı
    -0.08
     defiant
    -0.08
    æ´º
    -0.08
     Palace
    -0.08
    çī§
    -0.08
    åı¯è¡Į
    -0.07
    oin
    -0.07
    POSITIVE LOGITS
    å¤įåħ´
    0.10
    Poll
    0.09
    ä¹ĭ声
    0.09
    æĪ¾
    0.09
    ä»İæĿ¥æ²¡
    0.09
    ç¹ĩ
    0.09
    _poll
    0.09
    posites
    0.09
     Poll
    0.09
    awi
    0.09
    Activations Density 0.004%

    No Known Activations