© 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. 50194
    Prev
    Next
    INDEX
    Explanations

    most / least / fastest / smallest

    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
    esco
    -0.09
    æĽ´éĩįè¦ģçļĦ
    -0.08
    æĽ´å¥½çļĦ
    -0.08
    ä¸į妨
    -0.08
    chosen
    -0.08
    ót
    -0.08
    æģ°å½ĵ
    -0.08
    /goto
    -0.08
    /javascript
    -0.08
    orde
    -0.08
    POSITIVE LOGITS
    æľĢ容æĺĵ
    0.13
    æľĢéļ¾
    0.12
    æĺ¯æľĢ
    0.11
    æľĢ为
    0.10
    天èĬ±æĿ¿
    0.10
     least
    0.09
    è§Ħ模æľĢ大
    0.09
    ruk
    0.09
    ¹Ħ
    0.09
    èĢĥéªĮ
    0.09
    Activations Density 0.091%

    No Known Activations