© 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. 1139
    Prev
    Next
    INDEX
    Explanations

    network fabric and path

    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
    åIJĪä½ľä¼Ļä¼´
    -0.09
    rong
    -0.09
    ç²Ĺç³Ļ
    -0.09
    æ±Ń
    -0.08
    ç½®æį¢
    -0.08
     partners
    -0.08
    交æµģåIJĪä½ľ
    -0.08
    æ°ijå±ħ
    -0.08
    æ´»å¾Ĺ
    -0.08
    èĶļ
    -0.08
    POSITIVE LOGITS
    ä¸Ģå¼ł
    0.10
     bott
    0.09
    é«ĺæķĪçļĦ
    0.09
     Bott
    0.09
    çĵ¶é¢Ī
    0.09
    PathComponent
    0.08
     phy
    0.08
    æīij
    0.08
    è¿Ļå¼ł
    0.08
    _PHY
    0.08
    Activations Density 0.083%

    No Known Activations