© 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. 22487
    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
    æīĢæıIJä¾ĽçļĦ
    -0.10
    é¢ģåıij
    -0.09
    æľŁåĨħ
    -0.08
    åľ°åĿª
    -0.08
    ä¸Ģèµ·æĿ¥
    -0.08
    大è¡Ĺ
    -0.08
    eday
    -0.08
    çĤľ
    -0.08
     пÑĢеж
    -0.08
    éĢģå¾Ģ
    -0.07
    POSITIVE LOGITS
    æĮ¥
    0.11
    åĪĴ
    0.10
    å°±æѤ
    0.10
    åį¸
    0.09
    KIT
    0.09
    æİĢ
    0.09
     Cush
    0.09
    æ»ĭçĶŁ
    0.09
    quette
    0.09
     Tob
    0.09
    Activations Density 0.014%

    No Known Activations