© 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. 7032
    Prev
    Next
    INDEX
    Explanations

    glucose uptake, control, levels

    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
    ç¦ıå¾·
    -0.10
    éĢīåĿĢ
    -0.09
    æ¤Ĵ
    -0.09
    æ°ijæĹıæĸĩåĮĸ
    -0.08
    âĦħ
    -0.08
    æĬ¬å¤´
    -0.08
    修为
    -0.08
    edly
    -0.08
    rol
    -0.08
    road
    -0.08
    POSITIVE LOGITS
    忽
    0.10
    èĶĹ
    0.09
    .fromString
    0.09
     intolerance
    0.09
     syrup
    0.09
    amine
    0.08
    æľīçĽĬ
    0.08
    æŃī
    0.08
    éķ¶
    0.08
     Albuquerque
    0.08
    Activations Density 0.108%

    No Known Activations