© 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. 22315
    Prev
    Next
    INDEX
    Explanations

    touchdown passes

    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
    说æĪij
    -0.10
    ä¹Łæĺ¯ä¸Ģ个
    -0.09
     же
    -0.09
    æŀ¸
    -0.09
    å¼ĢæĿ¥
    -0.09
    one
    -0.09
    äºĨä¸Ģåı¥
    -0.09
    дол
    -0.09
     Äijá»ĵ
    -0.08
    åŃIJéĩĮ
    -0.08
    POSITIVE LOGITS
    /or
    0.11
    mand
    0.10
    仪
    0.09
     Mand
    0.09
    æŁıæŀĹ
    0.09
    illo
    0.09
    笳
    0.09
    rons
    0.09
    mu
    0.09
    errick
    0.08
    Activations Density 0.001%

    No Known Activations