© 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. 18302
    Prev
    Next
    INDEX
    Explanations

    pronouns and common nouns

    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
    åĵī
    -0.11
    .↵↵
    -0.10
    æĥ®
    -0.10
    éĨ´
    -0.09
    ä¸ĭéĿ¢å°±
    -0.09
     finally
    -0.09
    istar
    -0.09
    çī¹æ®ĬæĥħåĨµ
    -0.09
    backs
    -0.09
    æķ¬è¯·
    -0.09
    POSITIVE LOGITS
     zwar
    0.09
    ä¸Ģæĸ¹éĿ¢
    0.09
     Apparel
    0.09
    ERRU
    0.09
    ROWS
    0.08
    ä¸Ģæĸ¹éĿ¢æĺ¯
    0.08
    éĿĻ
    0.08
    åħĪæĺ¯
    0.08
    èĻ½è¯´
    0.08
    .getApp
    0.08
    Activations Density 0.608%

    No Known Activations