© 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. 22791
    Prev
    Next
    INDEX
    Explanations

    instead, contrasting alternatives

    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
    educt
    -0.10
    åĺīå¹´åįİ
    -0.09
    çļĦè®°å¿Ĩ
    -0.09
    åį¡æĭī
    -0.09
    çļĦçĶŁåij½
    -0.09
    owed
    -0.09
    ç¼ķ
    -0.09
    é¢IJ
    -0.09
    è¿ĺè®°å¾Ĺ
    -0.08
    è·¯ç¨ĭ
    -0.08
    POSITIVE LOGITS
    åŃ£
    0.09
    ä¾ĿéĿł
    0.09
    oze
    0.09
    rose
    0.09
    lider
    0.09
    OWER
    0.08
    ä¹ĭä¸ĭ
    0.08
     reliance
    0.08
    ä»ĸ们
    0.08
    为èĩªå·±
    0.08
    Activations Density 0.019%

    No Known Activations