© 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. 26763
    Prev
    Next
    INDEX
    Explanations

    assembly registers and numbers

    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
    anvas
    -0.09
    ä½Ĩä¸įéĻIJäºİ
    -0.09
    ----------------------------------------------------------------------
    -0.08
    _TYPEDEF
    -0.08
    aram
    -0.08
    -pic
    -0.08
    å§ĵ
    -0.08
    ucher
    -0.08
    è¿ŀè¿ŀ
    -0.08
    åľ¨ä¼łå¥ĩ
    -0.08
    POSITIVE LOGITS
    ï¼Īç¬ij
    0.08
    龸æ°Ķ
    0.08
    ç»Ļ她
    0.08
    çļĦéĤ£ç§į
    0.08
    AndGet
    0.07
    èĢĮåĩº
    0.07
    åĥįãģį
    0.07
    穷人
    0.07
    è¯ķè¯ķ
    0.07
    ä¼ģä¸ļæıIJä¾Ľ
    0.07
    Activations Density 2.263%

    No Known Activations