© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 10068
    Prev
    Next
    INDEX
    Explanations

    general generalizations generalised

    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
     combin
    -0.11
    combo
    -0.10
     Combo
    -0.10
    èµĽ
    -0.09
    ç»ĦåIJĪ
    -0.09
    ä¼ĹæīĢ
    -0.09
    å¼ĥ
    -0.09
    è¿°
    -0.09
    ä¸ĩç§ij
    -0.09
    éĴī
    -0.09
    POSITIVE LOGITS
     general
    0.10
    ä¸įåħį
    0.09
    éļ¾åħį
    0.09
    åĮºåŁŁåĨħ
    0.09
    æĻ®éģį
    0.09
    ä¾ĭå¤ĸ
    0.08
    æ¦Ĥæĭ¬
    0.08
    éĻ¤å¤ĸ
    0.08
    kins
    0.08
    æĪIJç«ĭ
    0.08
    Activations Density 0.050%

    No Known Activations