© 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. 53928
    Prev
    Next
    INDEX
    Explanations

    barcode scanner

    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
    nesc
    -0.09
    аÑĢам
    -0.09
    rat
    -0.09
    .Rendering
    -0.09
    ABCDEFGHI
    -0.09
    æĢģ
    -0.09
    loh
    -0.08
    觸
    -0.08
    è¹Ń
    -0.08
    诸侯
    -0.08
    POSITIVE LOGITS
    zet
    0.09
    åľ°å¸¦
    0.09
    inel
    0.08
    åĹ¡
    0.08
    zem
    0.08
    ä¸Ńå°ıåŀĭ
    0.08
    éĽı
    0.08
    éĥ¨åī¯
    0.08
    scanner
    0.08
    iem
    0.08
    Activations Density 0.029%

    No Known Activations