© 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. 61992
    Prev
    Next
    INDEX
    Explanations

    mobile and video content traffic

    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
    æľ¬ç½ijç«Ļ
    -0.10
    _tracker
    -0.10
    åľ¨åŃ¦æł¡
    -0.09
    æİĮæı¡
    -0.09
    erot
    -0.09
    bek
    -0.09
    çĻ¾å¹´
    -0.09
    对æīĭ
    -0.09
    æµ·çĽĹ
    -0.09
    awy
    -0.09
    POSITIVE LOGITS
     mobile
    0.11
    -mobile
    0.11
    移åĬ¨
    0.10
    Mobile
    0.09
    åĨ³æĪĺ
    0.09
     Mobile
    0.09
    mobile
    0.08
    .mobile
    0.08
    èĢIJå¿ĥ
    0.08
    饿
    0.08
    Activations Density 0.062%

    No Known Activations