© 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. 32914
    Prev
    Next
    INDEX
    Explanations

    Major League Baseball

    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
    è®Ńç»ĥ
    -0.11
    è¨ĵç·´
    -0.10
    第ä¸Ģ天
    -0.09
    èıģ
    -0.09
    .codes
    -0.08
    ãĥªãĥ³ãĤ°
    -0.08
    jang
    -0.08
    ura
    -0.08
    èĻ±
    -0.08
    æ±ĩéĽĨ
    -0.08
    POSITIVE LOGITS
    æľªæĪIJå¹´
    0.10
    itarian
    0.10
    严åİīæīĵåĩ»
    0.09
    åĽ´å¢Ļ
    0.09
    温馨
    0.09
    å¢Ļ
    0.09
    循
    0.08
    椽
    0.08
    å²ĺ
    0.08
    管çIJĨä¸Ńå¿ĥ
    0.08
    Activations Density 0.070%

    No Known Activations