© 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. 2432
    Prev
    Next
    INDEX
    Explanations

    brown rice or bread

    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
    etu
    -0.08
     unc
    -0.08
    åĩºåħ¥
    -0.08
    åĩĨ
    -0.08
    _COND
    -0.08
    æīĭ表
    -0.07
    ä¼¢
    -0.07
    _coverage
    -0.07
    ç½®
    -0.07
    stile
    -0.07
    POSITIVE LOGITS
    ç²ī
    0.11
    äºĨèĩªå·±çļĦ
    0.10
    éĤij
    0.09
    lasses
    0.09
    åľ¨ä¸Ģèµ·
    0.09
    gether
    0.09
    æĬĴ
    0.09
    edList
    0.09
    ilit
    0.09
    è·¯ç¨ĭ
    0.09
    Activations Density 0.001%

    No Known Activations