© 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. 61716
    Prev
    Next
    INDEX
    Explanations

    waiting for

    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
    æĪijåĸľæ¬¢
    -0.11
    æīĭä¸ŃçļĦ
    -0.11
    andom
    -0.09
    èĩªå·±åĸľæ¬¢
    -0.09
    è·¡
    -0.09
    inium
    -0.09
    éĢĤåIJĪèĩªå·±
    -0.09
    REE
    -0.09
    .readLine
    -0.09
    /cgi
    -0.09
    POSITIVE LOGITS
    å¥ī
    0.10
    åĿİ
    0.09
    é«
    0.09
    å·²ä¹ħ
    0.09
    riba
    0.09
    çĿĢ
    0.09
    æŁ¬
    0.09
    èĢĮä¸Ķ
    0.08
    ctest
    0.08
    çĿĢä»ĸ
    0.08
    Activations Density 0.019%

    No Known Activations