© 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. 3302
    Prev
    Next
    INDEX
    Explanations

    DIY projects and crafts

    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
    æĿª
    -0.09
    æ»ı
    -0.09
    ä»¿ä½Ľ
    -0.08
    ä¸¤å¼ł
    -0.08
    榷
    -0.08
    åı¯éĿłçļĦ
    -0.08
    çªĸ
    -0.08
    oden
    -0.08
    leh
    -0.08
    riba
    -0.08
    POSITIVE LOGITS
     DIY
    0.15
    åĬ¨æīĭ
    0.15
     diy
    0.12
    DI
    0.11
    åħ´ä¸ļ
    0.11
    åĪ¶ä½ľ
    0.10
    达人
    0.10
    èĩªè¡Į
    0.10
     Diy
    0.10
    èĩªåĬ©
    0.10
    Activations Density 0.285%

    No Known Activations