© 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
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 49537
    Prev
    Next
    INDEX
    Explanations

    questions starting with what or do

    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
    ä¸įä½Ĩ
    -0.09
    åįĴ
    -0.08
    èħ»
    -0.08
    对æĪijæĿ¥è¯´
    -0.08
    äºİæĺ¯æĪij
    -0.08
    ä½Ĩæĺ¯æĪij
    -0.08
    æĴµ
    -0.08
    agers
    -0.08
    aea
    -0.08
    æĹ¥æĬ¥ç¤¾
    -0.08
    POSITIVE LOGITS
    åį°è±¡æ·±åĪ»
    0.11
    oste
    0.10
    åħħå®ŀ
    0.09
    éļ¾
    0.09
    éĽ£
    0.08
    çªĿ
    0.08
    èĢģ乡
    0.08
    çİ°åľº
    0.08
    elay
    0.08
    è¯Ħ为
    0.08
    Activations Density 0.018%

    No Known Activations