© 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. 50315
    Prev
    Next
    INDEX
    Explanations

    positive descriptions of things

    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
    æµĵæµĵçļĦ
    -0.10
    enal
    -0.09
    è´
    -0.09
    çĭ¸
    -0.09
    è´¯
    -0.09
    åĴ©
    -0.09
    ients
    -0.09
     اÙĦØŃÙħÙĦ
    -0.08
    ä¼ļè®©ä½ł
    -0.08
    лен
    -0.08
    POSITIVE LOGITS
    -looking
    0.11
    ness
    0.10
    ãģª
    0.09
    à¸ĩาม
    0.09
    ly
    0.09
    åı¯éĿłçļĦ
    0.09
     Ker
    0.09
    -worthy
    0.09
    ä¸įåłª
    0.08
     ker
    0.08
    Activations Density 0.295%

    No Known Activations