© 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. 55427
    Prev
    Next
    INDEX
    Explanations

    margin or lead by

    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
    cuts
    -0.10
    éªģ
    -0.10
    é«ĺéĢŁ
    -0.09
     Spo
    -0.09
    èĭ±éĽĦ
    -0.09
    æİ¥åħ¥
    -0.09
    å¿ĻçĿĢ
    -0.09
    antic
    -0.08
    åı¦æľī
    -0.08
     hero
    -0.08
    POSITIVE LOGITS
    ç»ıçIJĨ
    0.10
    gp
    0.09
    è¿Ļ对äºİ
    0.08
    å½°æĺ¾
    0.08
    omen
    0.08
    èĢIJ
    0.08
    icher
    0.08
    å¹³æŶ
    0.08
    CLUDE
    0.08
    gal
    0.08
    Activations Density 0.010%

    No Known Activations