© 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. 27540
    Prev
    Next
    INDEX
    Explanations

    difference and result

    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
    ç½²
    -0.09
    çłĶ
    -0.08
    å¾ħ
    -0.08
    ãĤĵãģ§ãģĻãĤĪãģŃ
    -0.08
    å¤ļæĸ¹
    -0.08
    è´¥
    -0.08
    åĵİ
    -0.08
    ç¢į
    -0.08
    çıł
    -0.08
    åĪĨå¼Ģ
    -0.08
    POSITIVE LOGITS
    å·®ä¸įå¤ļ
    0.10
    ä½łå°±
    0.10
    å°±æľīäºĨ
    0.10
    å°±åı¯ä»¥äºĨ
    0.10
    è¿Ļå°±æĺ¯
    0.09
    å°±è¡ĮäºĨ
    0.09
    æĥ³åĥı
    0.09
    ç©¿éĢı
    0.09
    EFF
    0.09
    SCO
    0.09
    Activations Density 0.037%

    No Known Activations