© 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. 3389
    Prev
    Next
    INDEX
    Explanations

    fictional stories or places

    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
    ÑĢаÑģÑĤ
    -0.10
    eam
    -0.09
    ë¶Ģ
    -0.09
    .Cmd
    -0.09
    æĸ°æĪ¿
    -0.09
    ByPrimaryKey
    -0.09
    大å¦Ī
    -0.09
    çĶŁäº§æĢ»åĢ¼
    -0.09
    гÑĢани
    -0.08
    ë¶Ī
    -0.08
    POSITIVE LOGITS
    ç»İ
    0.10
    ized
    0.09
    çļĦåĬĽéĩı
    0.09
    ty
    0.08
    æĭįæĭį
    0.08
    ization
    0.08
    ä¸įç»ı
    0.08
    åĮĸçļĦ
    0.08
    ç±į
    0.08
    ilib
    0.08
    Activations Density 0.013%

    No Known Activations