© 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. 61638
    Prev
    Next
    INDEX
    Explanations

    poker or chess

    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
    ric
    -0.11
    ëģĶ
    -0.10
    sWith
    -0.10
    orary
    -0.09
    strup
    -0.09
    ãģªãģĭ
    -0.09
    ãĤĤãģĨ
    -0.09
    éļıå¤Ħ
    -0.09
    ny
    -0.08
    TING
    -0.08
    POSITIVE LOGITS
    æĬ¬å¤´
    0.10
    人çĶŁ
    0.10
    pedia
    0.09
    vascular
    0.09
    说æĺ¯
    0.09
    -like
    0.09
    çŃ¹çłģ
    0.09
    çıij
    0.09
    doll
    0.09
    ä¸įä¿¡
    0.09
    Activations Density 0.009%

    No Known Activations