© 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. 23053
    Prev
    Next
    INDEX
    Explanations

    concede

    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
    åŃ¦å®¶
    -0.12
    hood
    -0.10
    most
    -0.09
    éļĶçĥŃ
    -0.09
    ady
    -0.08
    inya
    -0.08
    letic
    -0.08
    vious
    -0.08
    å³Ļ
    -0.08
    诣
    -0.08
    POSITIVE LOGITS
    edly
    0.09
    ably
    0.09
     Livingston
    0.09
    碧æ¡Ĥ
    0.09
    缪
    0.09
    æĿ¯
    0.09
    ½æķ°
    0.09
    ìĤ¬íķŃ
    0.09
    [to
    0.08
    åŃº
    0.08
    Activations Density 0.009%

    No Known Activations