© 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. 29775
    Prev
    Next
    INDEX
    Explanations

    % followed by specific identifiers

    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
    plier
    -0.09
    ÑĩеÑģÑĤво
    -0.09
    è¦ģçŁ¥éģĵ
    -0.09
    umn
    -0.09
    ushman
    -0.08
    zos
    -0.08
    Aware
    -0.08
    壮大
    -0.08
    æľ¬äºº
    -0.08
    hip
    -0.08
    POSITIVE LOGITS
    ions
    0.11
    iling
    0.10
     (%)
    0.10
    çķ¢
    0.10
    å±Ī
    0.10
    atory
    0.09
    ç¾Į
    0.09
     chance
    0.09
    _chance
    0.09
     chances
    0.09
    Activations Density 0.119%

    No Known Activations