© 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. 34715
    Prev
    Next
    INDEX
    Explanations

    among others

    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
    anst
    -0.09
    keh
    -0.09
    smith
    -0.08
    зи
    -0.08
    udit
    -0.08
    æĿ¯
    -0.08
    comb
    -0.08
    expo
    -0.08
    è¿ĺ羣
    -0.08
    apture
    -0.08
    POSITIVE LOGITS
     ÑģÑĢеди
    0.12
    among
    0.12
     among
    0.11
    ä½Ĩä¸įéĻIJäºİ
    0.10
     ÙĪغÙĬرÙĩا
    0.10
    ä¾ĭåŃIJ
    0.10
     etc
    0.10
     others
    0.10
    äºĨå¾Īå¤ļ
    0.10
    ç§įç§į
    0.10
    Activations Density 0.040%

    No Known Activations