© 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. 19388
    Prev
    Next
    INDEX
    Explanations

    fractions and halves

    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
    éĴ®
    -0.10
    æĸĽ
    -0.09
    6
    -0.09
    8
    -0.09
    7
    -0.09
    4
    -0.09
    æĿ³
    -0.08
    9
    -0.08
    _NT
    -0.08
    ãģĵ
    -0.08
    POSITIVE LOGITS
    ä¸ĢåįĬ
    0.14
    åįĬ个
    0.14
    -half
    0.13
    åįĬ
    0.11
     полов
    0.11
    ä¸īåĪĨä¹ĭä¸Ģ
    0.10
     half
    0.10
     полÑĥ
    0.09
    half
    0.09
    ä¾ı
    0.09
    Activations Density 0.039%

    No Known Activations