© 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. 27246
    Prev
    Next
    INDEX
    Explanations

    feel it

    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
    icker
    -0.10
    容
    -0.10
    ply
    -0.10
    spm
    -0.09
    ester
    -0.09
    åĴ¨
    -0.09
    æĢ¥
    -0.09
    eur
    -0.09
    央
    -0.09
    emi
    -0.09
    POSITIVE LOGITS
    iras
    0.10
    ä½ļ
    0.10
    ainen
    0.10
    æĬ±æŃī
    0.10
    åħ±æĮ¯
    0.08
    çļĦæĿĥåĪ©
    0.08
    临港
    0.08
     ÑĥвеÑĢен
    0.08
    cke
    0.08
     deprivation
    0.08
    Activations Density 0.035%

    No Known Activations