© 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. 1336
    Prev
    Next
    INDEX
    Explanations

    not connected

    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
    æĪijå¸ĮæľĽ
    -0.10
    _TypeInfo
    -0.10
    icontrol
    -0.10
    åŃĺåľ¨äºİ
    -0.10
    azon
    -0.10
    лик
    -0.09
    åĢŁæѤ
    -0.09
    æĪijåı¯ä»¥
    -0.09
    åı¦è¡Į
    -0.09
    å¿«ä¹IJ
    -0.09
    POSITIVE LOGITS
     too
    0.14
    太
    0.13
    太å¤ļçļĦ
    0.13
    太è¿ĩ
    0.13
    too
    0.12
    太é«ĺ
    0.12
    太大
    0.11
    太å¤ļ
    0.11
    æĪĸèĢħæĺ¯
    0.11
    æľªèĥ½
    0.11
    Activations Density 0.388%

    No Known Activations