© 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. 56207
    Prev
    Next
    INDEX
    Explanations

    intuitive

    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
    ings
    -0.11
    hurst
    -0.08
     Ñģобой
    -0.08
    ä¸ĢåĽ¢
    -0.08
    ston
    -0.08
    utherford
    -0.08
    íģ¼
    -0.08
    ocking
    -0.08
    æľīèĩªå·±çļĦ
    -0.08
    пÑĢоÑģ
    -0.08
    POSITIVE LOGITS
    ively
    0.12
    è¿©
    0.09
    岸
    0.09
    pest
    0.09
    æĢ§å¼º
    0.09
    æĢ§çļĦ
    0.09
    ously
    0.09
    象
    0.09
    è¿ĻéĩĮæĺ¯
    0.09
    ities
    0.09
    Activations Density 0.008%

    No Known Activations