© 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. 5588
    Prev
    Next
    INDEX
    Explanations

    divided into groups

    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
     bó
    -0.08
    å¥ļ
    -0.08
    /API
    -0.08
    家åĸ»æĪ·æĻĵ
    -0.08
     phá
    -0.08
     tapped
    -0.08
    lide
    -0.08
    0
    -0.07
    å·²æľī
    -0.07
     اÙĦأج
    -0.07
    POSITIVE LOGITS
    fat
    0.09
    æ¢Ń
    0.09
    '),'
    0.09
    äºİæĺ¯æĪij
    0.09
    碼
    0.09
    æīĢ以æĪij
    0.09
    ocs
    0.09
    èħ®
    0.09
    _membership
    0.09
    æĭ¿åĩºæĿ¥
    0.09
    Activations Density 0.003%

    No Known Activations