© 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. 1362
    Prev
    Next
    INDEX
    Explanations

    OR and

    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
     kicker
    -0.09
    eling
    -0.09
    æĺ¯åı¯ä»¥
    -0.09
    éĩį建
    -0.09
    FUL
    -0.09
     Garland
    -0.09
    ä¸Ģ举
    -0.08
    utex
    -0.08
    ä»°
    -0.08
    åĵĪä½Ľ
    -0.08
    POSITIVE LOGITS
    hoff
    0.09
    ç½®
    0.08
    åĽ´çĿĢ
    0.08
    _modified
    0.08
    åıijæĮ¥ä½ľçĶ¨
    0.08
    /print
    0.08
    以为
    0.08
    ת×Ļ
    0.08
    æİĤ
    0.08
    åħħ足
    0.08
    Activations Density 0.029%

    No Known Activations