© 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. 30298
    Prev
    Next
    INDEX
    Explanations

    excessive or undue amounts

    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
    gression
    -0.10
    isphere
    -0.09
    èĶ¼
    -0.09
    encia
    -0.09
    ³
    -0.09
    ros
    -0.08
    -quarters
    -0.08
    že
    -0.08
    umbling
    -0.08
    alia
    -0.08
    POSITIVE LOGITS
    ément
    0.11
    å·§åIJĪ
    0.10
    èĩªä¿¡
    0.10
    æĭĺ
    0.09
    éļĶå£ģ
    0.09
    åħ³æ³¨
    0.09
    sen
    0.09
    à¸łà¸²à¸Ħ
    0.09
    ç©¿è¡£
    0.09
    ×Ļ׼
    0.09
    Activations Density 0.007%

    No Known Activations