© 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. 4447
    Prev
    Next
    INDEX
    Explanations

    Zamboni, Kimbap, Warrumbungle

    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
    icy
    -0.11
     Sandbox
    -0.10
    imity
    -0.10
    åıįè¿ĩæĿ¥
    -0.09
    lá
    -0.09
     возможноÑģÑĤи
    -0.09
    rnd
    -0.09
    æ´¼
    -0.09
    çĺ¾
    -0.08
    uality
    -0.08
    POSITIVE LOGITS
     liá»ĩt
    0.11
    棣
    0.10
    ez
    0.10
    ä¸ĩåįĥ
    0.10
    OfString
    0.09
    ucker
    0.09
    åľ°ä¸Ĭ
    0.09
    erset
    0.09
    ore
    0.09
    t
    0.09
    Activations Density 0.059%

    No Known Activations