© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 16920
    Prev
    Next
    INDEX
    Explanations

    spoke with, on, to, or of

    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
    à¹Į
    -0.11
    tk
    -0.10
    sWith
    -0.10
    AuthProvider
    -0.09
    sons
    -0.09
    æĺĨ
    -0.09
    è¾ħ
    -0.08
    dsa
    -0.08
    ä½łä¼ļåıijçİ°
    -0.08
    oul
    -0.08
    POSITIVE LOGITS
    anmar
    0.10
    ble
    0.10
    è¿ĩå¾Ĺ
    0.09
    ç¨ļ
    0.09
    анг
    0.09
    èĢĺ
    0.08
    irth
    0.08
    é¦ģ
    0.08
    anh
    0.08
    iped
    0.08
    Activations Density 0.010%

    No Known Activations