© 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. 49086
    Prev
    Next
    INDEX
    Explanations

    decode JWT

    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
    çģµæķı
    -0.09
    åªļ
    -0.09
    æ¶Įåħ¥
    -0.09
    aku
    -0.09
    社群
    -0.08
    泯
    -0.08
    æĸ¹ä¾¿
    -0.08
    éĶĢ
    -0.08
    acs
    -0.08
    èĻIJ
    -0.08
    POSITIVE LOGITS
    ç«Ļ
    0.10
    èİ«
    0.10
    å±ĭ
    0.10
    UCK
    0.09
    preload
    0.09
     compulsory
    0.09
    ä¸ĢæľŁ
    0.09
    lat
    0.09
     moz
    0.08
    ç«ĻçĤ¹
    0.08
    Activations Density 0.290%

    No Known Activations