© 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. 1721
    Prev
    Next
    INDEX
    Explanations

    fitness and shape

    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
    é¢Ĩ
    -0.09
    å®Įæķ´æĢ§
    -0.09
    ampus
    -0.09
    æģ¨ä¸įå¾Ĺ
    -0.09
    ieder
    -0.08
    tip
    -0.08
    æĻ¯å¾·
    -0.08
    çªł
    -0.08
    elli
    -0.08
    ober
    -0.08
    POSITIVE LOGITS
     fitness
    0.12
    åѱ
    0.10
    åģ¥èº«
    0.10
    å¤ĩæĪĺ
    0.09
    åģ¥åº·çļĦ
    0.09
    ÑĪа
    0.09
    fitness
    0.09
     Fitness
    0.09
    здоÑĢов
    0.09
     sức
    0.08
    Activations Density 0.014%

    No Known Activations