© 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. 3138
    Prev
    Next
    INDEX
    Explanations

    sign up or sign in

    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
     Tie
    -0.09
    éªĽ
    -0.09
    ABCDE
    -0.08
    çĤ¹éĴŁ
    -0.08
    豪
    -0.08
    _conditions
    -0.08
    ÑĩиÑģÑĤ
    -0.08
    SEMB
    -0.08
    ë³µ
    -0.08
     Sv
    -0.08
    POSITIVE LOGITS
    ä¹IJæĦı
    0.09
    3
    0.09
    athan
    0.09
    7
    0.09
    æĪĸèĢħ说
    0.09
    6
    0.09
    8
    0.08
    åIJĥäºı
    0.08
    9
    0.08
    atura
    0.08
    Activations Density 0.011%

    No Known Activations