© 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. 27015
    Prev
    Next
    INDEX
    Explanations

    issue in healthcare

    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
    豪
    -0.10
    æ¹ĸæ³Ĭ
    -0.09
    icare
    -0.08
    activ
    -0.08
    ossal
    -0.08
    åĨľå®¶
    -0.08
    èĩªåĪ¶
    -0.08
    errs
    -0.08
    quiet
    -0.08
     Quiet
    -0.08
    POSITIVE LOGITS
    borg
    0.09
    анÑģ
    0.09
    éªĪ
    0.08
    æıŃ
    0.08
    la
    0.08
    pisa
    0.08
    ç¹ģ
    0.08
    çªĪ
    0.08
    atal
    0.08
    ably
    0.08
    Activations Density 1.238%

    No Known Activations