© 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. 4490
    Prev
    Next
    INDEX
    Explanations

    supplementation and preparation

    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
     ML
    -0.10
    opp
    -0.09
     field
    -0.09
    (ml
    -0.09
     Gam
    -0.09
    견
    -0.09
    å¹³æķ´
    -0.08
    ML
    -0.08
    æĺ¯ä¸Ģéĥ¨
    -0.08
    æĨİ
    -0.08
    POSITIVE LOGITS
    æŶæĬ¥
    0.11
    è¿ĩåī©
    0.09
    çĽĪ
    0.09
    æĿ¥æºIJ
    0.09
    è¡¥åħħ
    0.09
    失踪
    0.09
    æ´ĭ
    0.09
    åħħè£ķ
    0.09
    _roles
    0.09
    è£ľ
    0.09
    Activations Density 0.112%

    No Known Activations