© 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. 38413
    Prev
    Next
    INDEX
    Explanations

    rush to install

    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
    温åĴĮ
    -0.10
    å¾ĺå¾Ĭ
    -0.09
    æī¿åıĹ
    -0.09
    ç¼ĵç¼ĵ
    -0.09
    _markup
    -0.09
    rive
    -0.08
    æ¼Ĥæµģ
    -0.08
    åīĸæŀIJ
    -0.08
    tif
    -0.08
    æľīå¾Ī大
    -0.08
    POSITIVE LOGITS
    赶æĿ¥
    0.14
    赶åĪ°
    0.13
    è¶ķ
    0.13
    æĬ¢
    0.12
    赶
    0.11
    æĬ¢åįł
    0.11
    赶紧
    0.11
    æIJ¶
    0.10
     haste
    0.10
    马æĭī
    0.09
    Activations Density 0.018%

    No Known Activations