© 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. 57104
    Prev
    Next
    INDEX
    Explanations

    butterfly, butterflies

    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
     Chá»ĭ
    -0.11
    åĪ©åĻ¨
    -0.10
    æŶåĢĻ
    -0.10
    abouts
    -0.09
    itor
    -0.09
    çł»
    -0.09
     BÃł
    -0.09
    OrUpdate
    -0.09
    éķª
    -0.09
    (crate
    -0.09
    POSITIVE LOGITS
    èĪ¬çļĦ
    0.10
    iates
    0.10
    ouv
    0.09
    èĪ¬
    0.09
    ä¸įå¼Ģ
    0.09
    ä¸ºæľŁ
    0.09
    ç¿ħèĨĢ
    0.08
    uant
    0.08
     flutter
    0.08
    ç¿ķ
    0.08
    Activations Density 0.017%

    No Known Activations