© 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. 2027
    Prev
    Next
    INDEX
    Explanations

    and/or

    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
    borne
    -0.10
    ä¸ĢæĹ¥
    -0.09
    SION
    -0.09
    èĥ½çľĭåĩº
    -0.09
    sett
    -0.09
    åĥı个
    -0.09
    zet
    -0.09
    hek
    -0.09
    owell
    -0.08
    CallCheck
    -0.08
    POSITIVE LOGITS
     or
    0.13
    /or
    0.13
    ãģ¾ãģŁãģ¯
    0.10
    æĪĸèĢħ
    0.10
     &
    0.09
    æĪĸ
    0.09
    æĪĸå¤ļæĪĸ
    0.09
     íĺ¹ìĿĢ
    0.09
    æĪĸèĢħæĺ¯
    0.09
    or
    0.08
    Activations Density 0.258%

    No Known Activations