© 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. 56756
    Prev
    Next
    INDEX
    Explanations

    acquired skills demonstrated standing identified

    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
    对æĪij们
    -0.14
    æ¯ĶæĪij
    -0.13
    å¦ĤæŀľæĪij们
    -0.12
    对æĪij
    -0.12
    为æĪij们
    -0.12
    ä¸ĭéĿ¢æĪij们
    -0.12
    ç»ĻæĪij们
    -0.11
    è·ŁæĪij
    -0.10
    æĪijè¿ĺ
    -0.10
    ç»ĻæĪij
    -0.10
    POSITIVE LOGITS
     oneself
    0.22
    ç¬ĶèĢħ
    0.14
    使人
    0.11
    让人
    0.10
    ÑĪе
    0.10
    该éĻ¢
    0.10
    å±ŀäºİèĩªå·±
    0.10
    à¸ķà¸Ļà¹Ģà¸Ńà¸ĩ
    0.10
    æŃ¤äºº
    0.09
    è®ĵ人
    0.09
    Activations Density 0.389%

    No Known Activations