© 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. 11065
    Prev
    Next
    INDEX
    Explanations

    equations and formulas

    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
    çļĦéĥ¨åĪĨ
    -0.09
    PTY
    -0.09
    ë¡Ŀ
    -0.09
    åľ°ä¸Ń
    -0.09
     Bram
    -0.09
    fä
    -0.09
    çĶ©
    -0.09
    essim
    -0.09
    оÑĩ
    -0.09
    æĬĺ
    -0.09
    POSITIVE LOGITS
    åħ¬å¼ı
    0.16
     formula
    0.14
    Formula
    0.13
    formula
    0.12
     formulas
    0.11
     Formula
    0.10
    _formula
    0.10
    çİĭåĽ½
    0.09
    ernal
    0.09
    sWith
    0.08
    Activations Density 0.104%

    No Known Activations