© 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. 19285
    Prev
    Next
    INDEX
    Explanations

    `usr/bin/env python`

    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
    è§Ħ模æľĢ大
    -0.11
    ings
    -0.10
    è°ĥåīĤ
    -0.09
    èĭ£
    -0.09
    inator
    -0.09
    æļ´éĽ¨
    -0.09
     ÑģмÑĭÑģл
    -0.09
    ç³ľ
    -0.09
    åľ¨äº¬
    -0.09
    åĨ·éĿĻ
    -0.08
    POSITIVE LOGITS
    angs
    0.08
    èĥĮ
    0.08
    dice
    0.08
    ulous
    0.08
    ther
    0.08
    è¿Ń
    0.07
    ìĺ¨
    0.07
    owler
    0.07
    gers
    0.07
    arde
    0.07
    Activations Density 0.002%

    No Known Activations