© 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. 17771
    Prev
    Next
    INDEX
    Explanations

    to + verb

    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
    å°ıé¾Ļ
    -0.09
    è¿ĽæĿ¥
    -0.09
    clair
    -0.09
    ä¸Ńæĸ°
    -0.08
    åħ¬åĬ¡
    -0.08
    å²Ĺ
    -0.08
    przed
    -0.08
     ÑĢанее
    -0.08
    太快
    -0.08
    ãģ¾ãģ¾
    -0.08
    POSITIVE LOGITS
    ä¸įæĸŃåľ°
    0.10
    èīºæľ¯
    0.09
    ä¸įæĸŃåĪĽæĸ°
    0.09
    æıIJä¾Ľ
    0.09
    еÑģÑĤв
    0.09
    ä¸Ŀ毫ä¸į
    0.09
    ä¸Ģå¾ĭ
    0.09
    cert
    0.09
    collections
    0.08
    çĶ¨æĪ·æıIJä¾Ľ
    0.08
    Activations Density 0.058%

    No Known Activations