© 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. 61455
    Prev
    Next
    INDEX
    Explanations

    starting lineup positions

    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
    æīĺ
    -0.10
    ç»Ī身
    -0.09
    ä¸īç»´
    -0.09
    çĵ¶é¢Ī
    -0.09
    æ»ļæ»ļ
    -0.09
    éĶIJ
    -0.09
    éģ¥è¿ľ
    -0.09
    æĴķ
    -0.09
    ibaba
    -0.08
    èı²
    -0.08
    POSITIVE LOGITS
    èĻİ
    0.10
    uong
    0.09
    æĽ¿è¡¥
    0.09
     Nord
    0.09
    Tumblr
    0.08
    iname
    0.08
    äº®çĽ¸
    0.08
    romium
    0.08
    _ENUM
    0.08
    aux
    0.08
    Activations Density 0.077%

    No Known Activations