© 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. 62344
    Prev
    Next
    INDEX
    Explanations

    relationship or function definitions

    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
    æĶ¯éħį
    -0.08
    ureka
    -0.08
    prox
    -0.07
    两ä¸ī
    -0.07
    éļ¾ä»¥
    -0.07
    ä¸Ģçľĭ
    -0.07
    tid
    -0.07
    utilities
    -0.07
    ä¸įåı¯èĥ½
    -0.07
    mong
    -0.07
    POSITIVE LOGITS
    è·ŁæĪij说
    0.14
    æī®æ¼Ķ
    0.14
     бÑĥдÑĥ
    0.12
    åı«æĪij
    0.11
    æī®
    0.11
    ç§ģãģĮ
    0.11
    å°ĨæĪIJ为
    0.11
    åħħå½ĵ
    0.10
    ç»ĻæĪij
    0.10
    使æĪij
    0.10
    Activations Density 0.024%

    No Known Activations