© 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. 49108
    Prev
    Next
    INDEX
    Explanations

    the [noun]

    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
    ç»Ļä»ĸ们
    -0.11
    éģij
    -0.10
    è¿Ļ个è¡Įä¸ļ
    -0.09
    ä¸Ģæł·
    -0.08
    æĺ¯ä¸Ģ座
    -0.08
    对æİ¥
    -0.08
    çű
    -0.08
    ä¸Ģ樣
    -0.08
    éĢł
    -0.08
    è¿Ļ群
    -0.08
    POSITIVE LOGITS
    iman
    0.10
    å¹´è½»
    0.09
    æ¸Ĭ
    0.09
    æIJŃéħį
    0.09
    ä¸įåı¯
    0.09
    AGE
    0.09
    çĤ¯
    0.09
    åŃĽ
    0.09
    uParam
    0.09
    SUP
    0.08
    Activations Density 0.089%

    No Known Activations