© 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. 27242
    Prev
    Next
    INDEX
    Explanations

    .Second

    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
    ä¸ºæľŁ
    -0.09
    缸ç»ĵåIJĪ
    -0.09
    çŃīåIJĦç§į
    -0.09
    åIJĦè¡Į
    -0.09
    ä¹İ
    -0.08
     nonetheless
    -0.08
    æĭĹ
    -0.08
    åıįæŃ£
    -0.08
    7
    -0.08
    泡泡
    -0.08
    POSITIVE LOGITS
    äºĮæĺ¯
    0.17
    åħ¶æ¬¡æĺ¯
    0.16
    åı¦ä¸Ģæĸ¹éĿ¢
    0.16
    åħ¶æ¬¡
    0.15
    ä¸İæѤ
    0.12
    ãģ§ãģĻãģĹ
    0.12
    ä¸İæѤåIJĮæŶ
    0.12
    .Second
    0.12
    ç´§æİ¥çĿĢ
    0.11
    èĢĮ对äºİ
    0.11
    Activations Density 0.411%

    No Known Activations