© 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. 53704
    Prev
    Next
    INDEX
    Explanations

    lets you

    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
    åĩºçİ°äºĨ
    -0.10
    igger
    -0.09
    æĢľ
    -0.09
    .boost
    -0.09
    (boost
    -0.09
    Ñħод
    -0.09
    带头人
    -0.09
    ä¸įæ¸ħæ¥ļ
    -0.09
    å®ŀåľ¨
    -0.09
    enance
    -0.09
    POSITIVE LOGITS
     us
    0.10
    æĩĤ
    0.10
    åıĤä¸İ
    0.10
    æģģ
    0.09
    è¿ĽæĿ¥
    0.09
     ÃŃch
    0.09
    tings
    0.09
    åģļçļĦäºĭæĥħ
    0.09
    lify
    0.09
    tres
    0.09
    Activations Density 0.038%

    No Known Activations