© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 21473
    Prev
    Next
    INDEX
    Explanations

    for all

    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
    æĬµæĬĹåĬĽ
    -0.09
    çŃĴ
    -0.08
    æ¿ĢåĬ¨
    -0.08
    alsa
    -0.08
     воÑģ
    -0.08
    è¯ļå®ŀ
    -0.08
    èĢį
    -0.08
    æĸĹ
    -0.08
    åIJĽ
    -0.08
    inox
    -0.08
    POSITIVE LOGITS
    etheless
    0.11
    åį»
    0.11
    åį´æĺ¯
    0.11
    åį´
    0.10
     Nonetheless
    0.10
     nonetheless
    0.10
    Nevertheless
    0.10
    æ±Ĺ
    0.10
    theless
    0.10
     ë¶Ī구íķĺê³ł
    0.10
    Activations Density 0.013%

    No Known Activations