© 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. 6616
    Prev
    Next
    INDEX
    Explanations

    channel your

    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
     <![
    -0.10
    udiant
    -0.09
     nic
    -0.09
    æŀľ
    -0.08
    èĪģ
    -0.08
    婦
    -0.08
    èĭŀ
    -0.08
    SSF
    -0.08
    æĬij
    -0.08
    emat
    -0.08
    POSITIVE LOGITS
    åĥı
    0.14
    类似äºİ
    0.13
    类似
    0.13
    çĬ¹å¦Ĥ
    0.11
    åĥıæĺ¯
    0.11
    å¦ĤåIJĮ
    0.11
    ä¿Ĺè¯Ŀ说
    0.10
    å°±åĥı
    0.10
     like
    0.10
    arcy
    0.10
    Activations Density 0.154%

    No Known Activations