© 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. 33067
    Prev
    Next
    INDEX
    Explanations

    serial port configuration, DDL, services

    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
    æİĮ
    -0.10
    sla
    -0.09
    berger
    -0.08
    çı¥
    -0.08
    PAD
    -0.08
    æĤį
    -0.08
    ajs
    -0.08
     Nä
    -0.08
    ria
    -0.08
    iddle
    -0.08
    POSITIVE LOGITS
     recru
    0.10
    è¿ĻæĶ¯
    0.09
    æĸ°ä¸ĸ纪
    0.09
    ä»ĩ
    0.09
    جاب
    0.09
    ое
    0.09
    ë§Į
    0.08
    usat
    0.08
    าม
    0.08
    é³Ŀ
    0.08
    Activations Density 0.002%

    No Known Activations