© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 47699
    Prev
    Next
    INDEX
    Explanations

    motor vehicle and related components

    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
    KEN
    -0.11
    å¿ĥåĬ¨
    -0.09
    åħĥå®Ŀ
    -0.09
    ukan
    -0.09
    ermal
    -0.09
    æݼ
    -0.09
    æ±¾
    -0.09
    že
    -0.09
    oard
    -0.09
    olec
    -0.09
    POSITIVE LOGITS
    ä»İä¸ļ人åijĺ
    0.09
    æıIJ款
    0.08
    hausen
    0.08
    orum
    0.08
    ä»İä¸ļèĢħ
    0.08
    adt
    0.08
    çĿ«
    0.08
    itch
    0.08
    emes
    0.08
    sted
    0.08
    Activations Density 0.006%

    No Known Activations