© 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. 18971
    Prev
    Next
    INDEX
    Explanations

    notes and colons

    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
    unta
    -0.08
    eer
    -0.08
    æĺ¯æľĢ好çļĦ
    -0.07
    éĻ¢éĻ¢å£«
    -0.07
    iling
    -0.07
    ç§Łè½¦
    -0.07
    ient
    -0.07
    æĪĸå¤ļæĪĸå°ij
    -0.07
    ä¾Ŀæ³ķ追究
    -0.07
    iska
    -0.07
    POSITIVE LOGITS
    notes
    0.13
     notes
    0.11
    -notes
    0.11
    å¤ĩ注
    0.10
    ValueCollection
    0.10
    edly
    0.10
     Bris
    0.10
    课åłĤ
    0.09
    .Note
    0.09
     Notes
    0.09
    Activations Density 0.055%

    No Known Activations