© 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. 35023
    Prev
    Next
    INDEX
    Explanations

    distance or travel with direction

    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
     thảo
    -0.11
     اÙĦÙģÙĤر
    -0.09
    riel
    -0.09
    -contrib
    -0.09
    obia
    -0.09
    èįī
    -0.09
    éĤ£ä¸ªæŶåĢĻ
    -0.09
     phép
    -0.09
    æĽ´å¼º
    -0.09
    æīĴ
    -0.09
    POSITIVE LOGITS
    æĪIJé¾Ļ
    0.09
    è¿Ļ两ç§į
    0.08
    æĪĺ
    0.08
    è¿Ľåĩº
    0.08
    unate
    0.08
    %%%%%%%%%%%%%%%%
    0.08
    uttle
    0.08
    ãģ«åĩº
    0.08
    \Log
    0.07
    sti
    0.07
    Activations Density 0.006%

    No Known Activations