© 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. 34303
    Prev
    Next
    INDEX
    Explanations

    time of day

    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
    ä¸ĵä¸ļæĬĢæľ¯
    -0.10
    èģĮä¸ļæĬĢæľ¯
    -0.09
    媳å¦ĩ
    -0.08
    å¾Īæ·±
    -0.08
    好ä¸į好
    -0.08
    计æıIJ
    -0.08
    é£İåIJ¹
    -0.08
    èĻ¢
    -0.08
    ¹Ħ
    -0.08
    ripper
    -0.08
    POSITIVE LOGITS
    lems
    0.10
    usat
    0.10
    åĥļ
    0.10
    ucken
    0.09
    快讯
    0.09
    adir
    0.09
    åİŁåħĪ
    0.09
    ãĥĭãĥ¥ãĥ¼ãĤ¹
    0.08
    _coverage
    0.08
    _CTL
    0.08
    Activations Density 0.157%

    No Known Activations