© 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. 48817
    Prev
    Next
    INDEX
    Explanations

    at this point

    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
    é¦ij
    -0.10
    åŃĶéĽĢ
    -0.10
    æĸ°è¥¿
    -0.10
    åŃ£åIJİ
    -0.10
    ä¾
    -0.09
    诡
    -0.08
    æĸ¹éĿ¢çļĦ
    -0.08
    onds
    -0.08
    aten
    -0.08
    eton
    -0.08
    POSITIVE LOGITS
    Sa
    0.09
    illes
    0.09
    abouts
    0.09
    orage
    0.09
    ures
    0.09
    æĥ¦
    0.08
    绢
    0.08
    sa
    0.08
    ioni
    0.08
     Dip
    0.08
    Activations Density 0.015%

    No Known Activations