© 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. 22922
    Prev
    Next
    INDEX
    Explanations

    frostbite or hypothermia or sickness

    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
    ä¿ĿæĮģçĿĢ
    -0.09
    çī¹å®ļ
    -0.09
    æļ§æĺ§
    -0.09
    æģº
    -0.08
    纳
    -0.08
    å°Ķæĸ¯
    -0.08
    ób
    -0.08
    å»ºåĽ½
    -0.08
    为ä¹ĭ
    -0.08
    èı²
    -0.08
    POSITIVE LOGITS
    çļĦåıijçĶŁ
    0.12
    ä¸İåIJ¦
    0.11
    严峻
    0.10
    çļĦåı¯èĥ½æĢ§
    0.10
    çݰ象
    0.10
    åı¯èĥ½æĢ§
    0.10
    é£İéĻ©
    0.09
    ModelError
    0.09
    eya
    0.09
     ocur
    0.09
    Activations Density 0.406%

    No Known Activations