© 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. 5875
    Prev
    Next
    INDEX
    Explanations

    community contributions

    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
    ç½®
    -0.10
    çľĭä¸įåĩº
    -0.10
    çľĭä¸įè§ģ
    -0.09
    urn
    -0.09
    å¹²æ¶ī
    -0.09
    æĬ±æŃī
    -0.09
    stown
    -0.09
     dú
    -0.08
    /mobile
    -0.08
    è¯ĪéªĹ
    -0.08
    POSITIVE LOGITS
    å¼ĢåıijèĢħ
    0.11
    åĽ½éĻħåIJĪä½ľ
    0.10
    å¿ĹæĦ¿èĢħ
    0.10
     community
    0.10
    é¢Ĩè¢ĸ
    0.10
    社åĮº
    0.09
     volunteer
    0.09
    æ´»è·ĥ
    0.09
     ÑģовеÑĢÑĪен
    0.09
    è´¡çĮ®
    0.09
    Activations Density 0.445%

    No Known Activations