© 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. 4077
    Prev
    Next
    INDEX
    Explanations

    flow, formation, derivative, injection, structure, electronics

    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
    åĬ©çIJĨ
    -0.11
    å½±
    -0.10
    åĬ©æīĭ
    -0.10
    apia
    -0.10
    пиÑĤ
    -0.10
    ä¸ĵçĶ¨
    -0.09
    ÑĦик
    -0.09
    -era
    -0.09
     Dou
    -0.09
     Gor
    -0.09
    POSITIVE LOGITS
    -heavy
    0.09
    大åĨĽ
    0.08
    ARS
    0.08
    天ä¸ĭ
    0.08
    天天
    0.08
    è®°å¾Ĺ
    0.08
    åĴ±
    0.08
    ä¸ĸçķĮ级
    0.08
    ç»Ŀ大å¤ļæķ°
    0.08
    å·¨é¢Ŀ
    0.08
    Activations Density 2.895%

    No Known Activations