© 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. 11726
    Prev
    Next
    INDEX
    Explanations

    roast meats

    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
    éĩĩ
    -0.09
    /Runtime
    -0.09
    uffix
    -0.09
    å¿«æĬ¥
    -0.09
    赤
    -0.09
    åĪ©åĻ¨
    -0.09
    åĬ¨æĢģ
    -0.08
    çķ¢
    -0.08
     trä
    -0.08
    æ¬Ħ
    -0.08
    POSITIVE LOGITS
    çĮªèĤī
    0.09
    èĭ«
    0.09
    epad
    0.09
     Hammond
    0.09
    票æĪ¿
    0.09
    çī¢çī¢
    0.09
    ä¸ĢæĹ¥
    0.08
    gia
    0.08
    _DEFINITION
    0.08
    åĽŀæĬ¥
    0.08
    Activations Density 0.145%

    No Known Activations