© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 37833
    Prev
    Next
    INDEX
    Explanations

    insects and IT

    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
    è¿Ī
    -0.09
    .Cursor
    -0.09
     eslint
    -0.08
    åħij
    -0.08
    æħĪ
    -0.08
     quad
    -0.08
     dens
    -0.08
    GLOBALS
    -0.08
    arker
    -0.08
    rott
    -0.08
    POSITIVE LOGITS
    åĬ¨éĿĻ
    0.11
    磼
    0.10
    çªĴæģ¯
    0.10
    ç»ĵå±Ģ
    0.09
    oly
    0.09
    rost
    0.09
    çļĦèĥĮåIJİ
    0.09
     Sites
    0.09
     Barn
    0.09
    å¸ĪèµĦ
    0.09
    Activations Density 0.002%

    No Known Activations