© 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. 34762
    Prev
    Next
    INDEX
    Explanations

    4 followed by a word

    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
     Vas
    -0.09
    (Photo
    -0.08
    éĥĬ
    -0.08
    çIJĨå·¥
    -0.08
    orting
    -0.08
    æĿ¯
    -0.08
    Chron
    -0.08
    人éĥ½
    -0.08
    æİı
    -0.07
    åĪĨæĺİ
    -0.07
    POSITIVE LOGITS
    bidden
    0.11
    éĢµ
    0.10
    éĤij
    0.10
    å¢ŀè¿Ľ
    0.09
    è¿Ļ对
    0.09
    ces
    0.09
    å¾ĩ
    0.09
     ÄijoÃłn
    0.09
    çŃĶ
    0.09
    tring
    0.09
    Activations Density 0.039%

    No Known Activations