© 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. 10250
    Prev
    Next
    INDEX
    Explanations

    specific entities or structures

    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
    说ä¸įåĩº
    -0.09
    vida
    -0.09
    usher
    -0.09
    ä¹Łä¸įæķ¢
    -0.09
    çļĦ好
    -0.09
    вед
    -0.09
    CRYPT
    -0.09
    ëįķ
    -0.09
    ç²¾å¯Ĩ
    -0.09
    oric
    -0.08
    POSITIVE LOGITS
    /or
    0.09
     inspir
    0.08
     forb
    0.08
    æĢİä¹ĪåĽŀäºĭ
    0.08
     Leeds
    0.08
    常å·ŀ
    0.07
     Raw
    0.07
     raw
    0.07
    èĢģå¹´
    0.07
    bps
    0.07
    Activations Density 3.492%

    No Known Activations