© 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. 30018
    Prev
    Next
    INDEX
    Explanations

    maneuver

    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
    creen
    -0.11
    ırl
    -0.09
    æł·çļĦ
    -0.09
    ä¸ľè¥¿
    -0.09
    fur
    -0.09
    ented
    -0.09
    arus
    -0.09
    owing
    -0.08
    iny
    -0.08
    htable
    -0.08
    POSITIVE LOGITS
    ä¸Ģçķª
    0.13
    èĩªå¦Ĥ
    0.12
    æĽ²æĬĺ
    0.10
    ä¸Ńå¿ĥåŁİå¸Ĥ
    0.10
    tte
    0.09
    ettes
    0.09
    osity
    0.09
    à´Ļ
    0.09
    /function
    0.09
    å¸ĤæķĻèĤ²
    0.08
    Activations Density 0.007%

    No Known Activations