© 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. 26986
    Prev
    Next
    INDEX
    Explanations

    And

    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
    èĩªåľ¨
    -0.10
    Priv
    -0.09
    ovi
    -0.09
     Priv
    -0.09
    issen
    -0.09
    ä¸įä¸ĭ
    -0.09
    å®ľå±ħ
    -0.08
    éĢļè¡Į
    -0.08
    å°±åľ¨
    -0.08
    æ»ĵ
    -0.08
    POSITIVE LOGITS
    æľīçĶ¨çļĦ
    0.09
    å®Įç¾İçļĦ
    0.09
    éħIJ
    0.08
    ç¼ĸ
    0.08
    龸
    0.08
     пÑĥÑĤ
    0.08
    å¾Ĺ天
    0.08
     plus
    0.08
    è¿
    0.08
    _scope
    0.08
    Activations Density 0.034%

    No Known Activations