© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 37674
    Prev
    Next
    INDEX
    Explanations

    foreign names and words

    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
    æĥ³æĥ³
    -0.11
    åķī
    -0.10
    inus
    -0.09
    ä¹ĭ乡
    -0.09
    éĺħ
    -0.09
    .lesson
    -0.09
    éĿ¢åħ·
    -0.09
    æ¸İ
    -0.09
    çĿģå¼Ģ
    -0.08
    èĻij
    -0.08
    POSITIVE LOGITS
    æĿ¥åĽŀ
    0.09
    è¦ģç´§
    0.09
    zie
    0.08
    éĶ
    0.08
    éºĴ
    0.08
    ardon
    0.08
    å¨ģ
    0.08
     кÑĢÑĥг
    0.08
    azar
    0.08
     Arms
    0.08
    Activations Density 0.009%

    No Known Activations