© 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. 11781
    Prev
    Next
    INDEX
    Explanations

    2 followed by U, 1, 0, Limited, Consult

    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
    ibt
    -0.09
    à¹Į
    -0.09
    esis
    -0.09
    GBK
    -0.09
    BOSE
    -0.08
    isco
    -0.08
    _FD
    -0.08
    enal
    -0.08
    ock
    -0.08
    entes
    -0.08
    POSITIVE LOGITS
    象
    0.09
    ANCH
    0.09
    çļĦæĹ¥åŃIJ
    0.09
    ãĤĬ
    0.09
    èĪįå¾Ĺ
    0.09
    æ¡Ģ
    0.09
    drawing
    0.08
    å²Ń
    0.08
    å¿ĥ头
    0.08
    纸ä¸Ĭ
    0.08
    Activations Density 0.308%

    No Known Activations