© 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. 56017
    Prev
    Next
    INDEX
    Explanations

    quest

    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
    teen
    -0.10
    vester
    -0.10
    esco
    -0.09
    ActionResult
    -0.09
    out
    -0.09
     Ñģебе
    -0.09
    éĩijæ²Ļ
    -0.08
    ä¿ĥæĪIJ
    -0.08
    åħ±éĿĴåĽ¢
    -0.08
    çĬ¶åħĥ
    -0.08
    POSITIVE LOGITS
    ÙĬØŃ
    0.09
    éĤĤ
    0.09
    大家åı¯ä»¥
    0.09
    人家
    0.09
    大大å°ıå°ı
    0.08
    oref
    0.08
    æĹ¥åŃIJ
    0.08
    ional
    0.08
    çIJĨæĥ³ä¿¡å¿µ
    0.08
    erged
    0.08
    Activations Density 0.003%

    No Known Activations