© 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. 49594
    Prev
    Next
    INDEX
    Explanations

    hat trick, cycle, homer, baseball hits

    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
    奴
    -0.10
    ç¢İçīĩ
    -0.09
    èĪŁ
    -0.09
    æ¸ł
    -0.09
    åIJĿ
    -0.09
    æĹłè®º
    -0.09
     dù
    -0.09
    èĨ¨
    -0.09
     mü
    -0.09
    çĤī
    -0.08
    POSITIVE LOGITS
    골
    0.09
    彩èī²
    0.08
    usp
    0.08
    -go
    0.08
    _ca
    0.08
    dispose
    0.08
    æ·±æ·±åľ°
    0.08
    åħ³éŨ
    0.08
     çĻ
    0.08
    agger
    0.08
    Activations Density 0.046%

    No Known Activations