© 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. 6540
    Prev
    Next
    INDEX
    Explanations

    happy to meet 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
    å¤±æľĽ
    -0.10
    è´¯
    -0.09
     spoiler
    -0.09
    æĻ®æĥł
    -0.09
     spoilers
    -0.09
    ORTH
    -0.08
    åİ»äºĨ
    -0.08
    å§Ķ
    -0.08
    $http
    -0.08
    plib
    -0.08
    POSITIVE LOGITS
    ç»Īäºİ
    0.11
    ynes
    0.10
     sight
    0.10
    ä½łåĢij
    0.09
    å¿ĺäºĨ
    0.09
     Sight
    0.09
    æ²IJæµ´
    0.09
    ä½łåĸľæ¬¢
    0.09
    欢è¿İ大家
    0.09
     Hoy
    0.09
    Activations Density 0.014%

    No Known Activations