© 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. 22143
    Prev
    Next
    INDEX
    Explanations

    competitive offerings

    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
    scal
    -0.09
    赤
    -0.08
    thon
    -0.08
    常æĢģ
    -0.08
    Sizer
    -0.08
    ungs
    -0.08
    ç´ł
    -0.08
    uchi
    -0.08
    enthal
    -0.08
    å¿ĥä¸Ń
    -0.08
    POSITIVE LOGITS
    ç«ŀ
    0.12
    competitive
    0.11
     competitive
    0.11
     Competitive
    0.10
    Compet
    0.10
    åĩºæīĭ
    0.10
    诱
    0.10
    notated
    0.09
    ä¸įåı¯æĢĿè®®
    0.09
    ç«ŀäºīåĬĽ
    0.09
    Activations Density 0.012%

    No Known Activations