© 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. 16857
    Prev
    Next
    INDEX
    Explanations

    on + noun

    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
    å¸ĺ
    -0.09
     Lad
    -0.09
    Ñĥв
    -0.09
     Lance
    -0.08
    untime
    -0.08
     parachute
    -0.08
    人äºĭ
    -0.08
    äºĭåIJİ
    -0.08
    ç¼Ĭ
    -0.08
     Lö
    -0.08
    POSITIVE LOGITS
    ä¸ĬçļĦ
    0.11
    icer
    0.10
    éĤ£ä½į
    0.10
    ãĤĴãģ¤ãģij
    0.10
    éĻĦ
    0.10
    身ä¸Ĭ
    0.10
    /off
    0.10
    ä½ĵè´´
    0.09
    è¾Ľåĭ¤
    0.09
    è¿Ļä½į
    0.09
    Activations Density 0.329%

    No Known Activations