© 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. 51208
    Prev
    Next
    INDEX
    Explanations

    customer service

    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
    çļĦç¡®
    -0.11
    馥
    -0.10
    enger
    -0.10
    ÑĢоÑģ
    -0.09
    (Abstract
    -0.09
    uges
    -0.09
    åĪĩ
    -0.09
    éī´
    -0.09
    å»ĵ
    -0.09
    kest
    -0.09
    POSITIVE LOGITS
    jos
    0.09
    大å±Ģ
    0.08
     skl
    0.08
     Cone
    0.08
    ŀæĢ§
    0.08
    åIJĽåŃIJ
    0.08
    (redis
    0.08
     FLAGS
    0.07
    oze
    0.07
    è³¢
    0.07
    Activations Density 0.007%

    No Known Activations