© 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. 902
    Prev
    Next
    INDEX
    Explanations

    had not / if had

    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
    å¾Ī满æĦı
    -0.10
    éļ¾åħį
    -0.09
    iani
    -0.09
    æĸ°åĬł
    -0.09
    _nat
    -0.08
    ä¸įåı¯éģ¿åħį
    -0.08
    åĬ¨äºº
    -0.08
     Peoples
    -0.08
    æĥħå½¢
    -0.08
    å¾Ĺå¾Ī好
    -0.08
    POSITIVE LOGITS
    lore
    0.10
    åĩłåĪĨ
    0.09
    éªĸ
    0.09
    ç¦ıçī¹
    0.09
    çĹĶ
    0.08
    ahoo
    0.08
    lek
    0.08
    osit
    0.08
    esson
    0.08
     Intervention
    0.08
    Activations Density 0.014%

    No Known Activations