© 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. 10669
    Prev
    Next
    INDEX
    Explanations

    ancient scrolls and books

    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
    èĻij
    -0.09
    综
    -0.09
    aylor
    -0.09
    æ³¾
    -0.09
    éº»æľ¨
    -0.08
    æĸ©
    -0.08
    æģ»
    -0.08
    éĻĮ
    -0.08
    ç´łè´¨
    -0.08
     Pins
    -0.08
    POSITIVE LOGITS
    解éĶģ
    0.12
    è®°è½½
    0.12
    çĽ¸ä¼ł
    0.11
    ä¼łæī¿
    0.11
    ä¼łæİĪ
    0.11
    æµģä¼ł
    0.11
    åIJ¯ç¤º
    0.11
    羣çIJĨ
    0.11
    ä¸ĸ代
    0.11
    ç§ĺå¯Ĩ
    0.10
    Activations Density 0.077%

    No Known Activations