© 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. 32373
    Prev
    Next
    INDEX
    Explanations

    H2O2 or O2

    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
    ä»Ģä¹Īéĥ½
    -0.11
    大家
    -0.10
    ckett
    -0.10
    请大家
    -0.09
    大家åı¯ä»¥
    -0.09
    éĢ®
    -0.09
    .NewReader
    -0.09
    æŃ¹
    -0.09
    æľīæĦıæĢĿ
    -0.09
    æĹ©çĤ¹
    -0.09
    POSITIVE LOGITS
    ktor
    0.08
    ient
    0.08
     laps
    0.08
     original
    0.08
     lbs
    0.08
    èIJ¼
    0.08
    icha
    0.07
    æ¦Ĥ
    0.07
    pek
    0.07
     Baxter
    0.07
    Activations Density 0.030%

    No Known Activations