© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 37026
    Prev
    Next
    INDEX
    Explanations

    inserting into

    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
    å¾Ļ
    -0.10
    ãģĵãģ¨ãģ§
    -0.09
    utt
    -0.09
    å¼ĢåĪĽ
    -0.08
    çīĭ
    -0.08
    ä½İ头
    -0.08
     inaugur
    -0.08
    æ®ĭçķĻ
    -0.08
    bak
    -0.08
    nt
    -0.08
    POSITIVE LOGITS
    æıĴåħ¥
    0.14
    into
    0.13
    Into
    0.13
     INTO
    0.13
    æ¥Ķ
    0.13
    (insert
    0.12
    .Insert
    0.12
    æıĴ
    0.12
     vÃło
    0.12
     into
    0.12
    Activations Density 0.088%

    No Known Activations