© 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. 62859
    Prev
    Next
    INDEX
    Explanations

    foreign languages

    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
    æĬĺ
    -0.09
    éĿ¢ä¸´
    -0.08
     Ñĥзн
    -0.08
    æij
    -0.08
    è§Ħ
    -0.08
    ÑģÑĤи
    -0.08
    æĭ§
    -0.08
     ~>
    -0.08
    ä¹Ļ
    -0.08
    è¿
    -0.08
    POSITIVE LOGITS
    è¿Ļéĥ¨
    0.11
    è¯įæĿ¡
    0.10
    å·²äºİ
    0.10
    奢
    0.09
    ä¸ĭæĿ¥çļĦ
    0.09
    à¸īà¸ļ
    0.09
    ç¦ģå¿Į
    0.09
    è¾¹éĻħ
    0.09
    è¿Ļ款
    0.09
    .comp
    0.09
    Activations Density 0.276%

    No Known Activations