© 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. 30980
    Prev
    Next
    INDEX
    Explanations

    MySQL database operations

    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
    aqu
    -0.10
    å±ĤéĿ¢
    -0.09
    atern
    -0.09
     roma
    -0.08
    åº
    -0.08
    çIJĨæĥ³çļĦ
    -0.08
    HAM
    -0.08
    zent
    -0.08
     EITHER
    -0.08
    zar
    -0.08
    POSITIVE LOGITS
    说æĪij
    0.09
    shine
    0.09
     Antony
    0.09
     вели
    0.09
     Cald
    0.09
    ä¸IJ
    0.08
    sWith
    0.08
    åģ»
    0.08
    nu
    0.08
    ä¼Łå¤§
    0.08
    Activations Density 0.077%

    No Known Activations