© 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. 39430
    Prev
    Next
    INDEX
    Explanations

    midfielders and midfield positions

    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»·éĴ±
    -0.10
    å®ĺ
    -0.10
    Rated
    -0.09
    _iff
    -0.09
    ç¦ıå¾·
    -0.09
     ØŃÙĪ
    -0.09
    鹧
    -0.09
    vette
    -0.09
    æł·çļĦ
    -0.09
    itches
    -0.09
    POSITIVE LOGITS
    è¿©
    0.08
    诸
    0.08
    3
    0.08
    æĭĺ
    0.08
    er
    0.08
    /or
    0.08
    ator
    0.08
    ers
    0.08
    4
    0.08
    ино
    0.08
    Activations Density 0.003%

    No Known Activations