© 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. 32593
    Prev
    Next
    INDEX
    Explanations

    processes

    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
    丰åİļ
    -0.11
    è¡ĮåĬ¨è®¡åĪĴ
    -0.11
    acy
    -0.10
    adders
    -0.10
    åĻ¨æ¢°
    -0.09
    amen
    -0.09
    趣
    -0.09
    ası
    -0.08
    -pill
    -0.08
    ayı
    -0.08
    POSITIVE LOGITS
    è¿ĩç¨ĭ
    0.18
     process
    0.17
    process
    0.16
    (process
    0.15
     processes
    0.15
     пÑĢоÑĨеÑģÑģ
    0.14
    æµģç¨ĭ
    0.14
    éģİç¨ĭ
    0.13
    /process
    0.13
     processo
    0.13
    Activations Density 0.149%

    No Known Activations