© 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. 39834
    Prev
    Next
    INDEX
    Explanations

    ice hockey

    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
    burgh
    -0.11
    ihad
    -0.10
    uto
    -0.10
    åı¯è§ĨåĮĸ
    -0.09
    UTO
    -0.09
    VML
    -0.09
    _both
    -0.09
    IBUT
    -0.09
    åİķ
    -0.08
    .converter
    -0.08
    POSITIVE LOGITS
    iji
    0.10
    èĽ©
    0.09
    é¢Į
    0.09
    åı¼
    0.09
    纵深
    0.09
    ä¸ŀ
    0.09
    笳
    0.09
    füh
    0.09
    ä¼ĺ
    0.08
    åѦçĶŁä»¬
    0.08
    Activations Density 0.070%

    No Known Activations