© 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. 37739
    Prev
    Next
    INDEX
    Explanations

    Department, Office, Agency names

    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
    yms
    -0.09
     gent
    -0.08
    æĪIJ为ä¸ĢåIJį
    -0.08
    å¼Ģåı£
    -0.08
    tte
    -0.08
    gent
    -0.08
     ov
    -0.08
    har
    -0.08
     sentiment
    -0.08
     Gent
    -0.08
    POSITIVE LOGITS
    å¸ĮæľĽéĢļè¿ĩ
    0.11
    忽æĤł
    0.10
    é¼ĵåĬ±
    0.10
    éĿŀ常好çļĦ
    0.10
    主åĬŀ
    0.10
    åIJĦåĮº
    0.10
    为äºĨ让
    0.10
    ä¸īæĸ¹
    0.10
    çīµå¤´
    0.10
     sponsors
    0.09
    Activations Density 0.142%

    No Known Activations