© 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. 5666
    Prev
    Next
    INDEX
    Explanations

    teammate

    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
    -0.11
    èĢģå¦Ī
    -0.10
    è¿Ļåħ¶ä¸Ń
    -0.09
    ANI
    -0.09
    quo
    -0.09
    æĪIJ为ä¸ĢåIJį
    -0.09
    iers
    -0.09
    uard
    -0.09
    stances
    -0.09
    家åħ·
    -0.09
    POSITIVE LOGITS
    们çļĦ
    0.10
    åĢij
    0.10
    åĴĮ社ä¼ļ
    0.10
    们
    0.09
    -sama
    0.09
    hood
    0.09
    ookie
    0.09
    们éĥ½
    0.09
    æµ´
    0.08
    nad
    0.08
    Activations Density 0.011%

    No Known Activations