© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 53291
    Prev
    Next
    INDEX
    Explanations

    code generated by

    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
    æľ¬ç½ijç«Ļ
    -0.09
    èĴĻ
    -0.09
    иÑĪÑĮ
    -0.09
    ACING
    -0.08
    -notification
    -0.08
    oir
    -0.08
    otes
    -0.08
    omain
    -0.08
     enc
    -0.08
     spl
    -0.08
    POSITIVE LOGITS
    åıĸåĨ³
    0.11
     Webster
    0.09
    楣
    0.09
    æ²»çIJĨ
    0.08
    ada
    0.08
    天天
    0.08
    è¿Ļ段
    0.08
    æĥłæ°ij
    0.08
    ued
    0.08
    èĤ¥
    0.08
    Activations Density 0.009%

    No Known Activations