© 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. 5837
    Prev
    Next
    INDEX
    Explanations

    corporate entities and .com domains

    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
    lam
    -0.08
    reate
    -0.08
    tober
    -0.08
    igt
    -0.08
    sing
    -0.08
    _Element
    -0.08
    çķĮ
    -0.08
    sert
    -0.08
    igli
    -0.08
    IDO
    -0.07
    POSITIVE LOGITS
    æľīéĻIJåħ¬åı¸
    0.14
    éĽĨåĽ¢èĤ¡ä»½
    0.13
    æľīéĻIJ责任
    0.12
    è¿Ĥ
    0.10
    æ¼Ķèīº
    0.10
    èĤ¡ä»½
    0.10
    æłª
    0.09
    å±ĢéĻIJäºİ
    0.09
    游æĪıæĵįä½ľ
    0.09
    è°ª
    0.09
    Activations Density 0.261%

    No Known Activations