© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 7112
    Prev
    Next
    INDEX
    Explanations

    US states and places

    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
    æ¯ķç«Łæĺ¯
    -0.09
    åijĹ
    -0.09
    incer
    -0.08
    åľ¨åĮĹ京
    -0.08
    ãĥ¡ãĥ³
    -0.08
    é£ĺ
    -0.08
    对çŃĸ
    -0.08
    enga
    -0.08
    éĽªå±±
    -0.08
    ksi
    -0.08
    POSITIVE LOGITS
    å¢ĥåĨħ
    0.09
    å¥ł
    0.09
     Carb
    0.09
    pec
    0.08
    ä¸İä¸ŃåĽ½
    0.08
    å¤ļå¹´æĿ¥
    0.08
    nown
    0.08
    ä¾ĽéĶĢ
    0.08
    积æŀģåĵįåºĶ
    0.08
     nữa
    0.08
    Activations Density 0.103%

    No Known Activations