© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 51556
    Prev
    Next
    INDEX
    Explanations

    name origins and reasons

    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
    rawid
    -0.08
    èĤĵ
    -0.08
    wo
    -0.08
     gum
    -0.07
    èĨľ
    -0.07
    æĢİä¹Ī说
    -0.07
    èĪĮå°ĸ
    -0.07
    _CLI
    -0.07
    urances
    -0.07
    isphere
    -0.07
    POSITIVE LOGITS
    ç»´å¥ĩ
    0.10
    åĬŀåѦ
    0.10
    ä¸ļåĨħ
    0.09
    龸æ°Ķ
    0.09
    æ¯ĴæĢ§
    0.09
     Seas
    0.09
    è¿Ļ个åIJįåŃĹ
    0.09
    ä½Ĩå®ŀéĻħä¸Ĭ
    0.09
    称ä¹ĭ为
    0.09
    chrom
    0.09
    Activations Density 0.170%

    No Known Activations