© 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. 34329
    Prev
    Next
    INDEX
    Explanations

    film noir and crime fiction

    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
     Affero
    -0.11
    çĶŁæ®ĸ
    -0.10
    åĭŁ
    -0.10
    -router
    -0.10
     Minority
    -0.10
    榻
    -0.09
     èĭ¥è¦ģ
    -0.09
    ichel
    -0.09
    å²±
    -0.09
    åĿŁ
    -0.09
    POSITIVE LOGITS
    èŃ¦å¯Ł
    0.09
    æ¯Ĵåĵģ
    0.09
     ICO
    0.09
    åĪijèѦ
    0.09
    èѦåĬ¡
    0.08
    æ±Łæ¹ĸ
    0.08
    åĨī
    0.08
    贪婪
    0.08
    ç¦ģæ¯Ĵ
    0.08
     Police
    0.08
    Activations Density 0.057%

    No Known Activations