© 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. 57810
    Prev
    Next
    INDEX
    Explanations

    important [followed by significant noun/descriptor]

    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
    åIJįåĪĹåīįèĮħ
    -0.09
     hứng
    -0.08
    ses
    -0.08
    ä¸Ģåı¥è¯Ŀ
    -0.08
    /API
    -0.08
    好åĿı
    -0.08
    大çĨĬçĮ«
    -0.08
    sing
    -0.08
    æľĢéļ¾
    -0.08
    rank
    -0.08
    POSITIVE LOGITS
    omic
    0.09
    æĬĬæīĭ
    0.09
     enough
    0.09
     clue
    0.09
    转身
    0.09
    è§ģ解
    0.08
    ä¸įåħĭ
    0.08
    æĬī
    0.08
    nym
    0.08
    ATS
    0.08
    Activations Density 0.059%

    No Known Activations