© 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. 4301
    Prev
    Next
    INDEX
    Explanations

    ade / chocolate

    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
    çľĩ
    -0.10
    äºĨ大éĩıçļĦ
    -0.09
    æķ°çĽ®
    -0.08
    iment
    -0.08
    undi
    -0.08
    æIJı
    -0.08
    ä»İæĿ¥æ²¡
    -0.08
    çķª
    -0.08
    olv
    -0.08
    .regex
    -0.08
    POSITIVE LOGITS
    iram
    0.09
    ends
    0.09
     eBooks
    0.09
    æīĢä»¥åľ¨
    0.09
    ialias
    0.09
    ennes
    0.08
    educt
    0.08
    ãĤĵãģª
    0.08
    icator
    0.08
    AZE
    0.08
    Activations Density 0.005%

    No Known Activations