© 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. 48261
    Prev
    Next
    INDEX
    Explanations

    gloss or glossy

    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
    åĢij
    -0.09
    ase
    -0.09
    ees
    -0.09
     Arms
    -0.09
    stead
    -0.09
    umi
    -0.08
    theless
    -0.08
    沤
    -0.08
    ish
    -0.08
    apos
    -0.08
    POSITIVE LOGITS
    ç°ª
    0.09
    еÑĢе
    0.09
    ingleton
    0.09
    sar
    0.09
    æĺ¯éĿŀ
    0.09
    ãģ£ãģįãĤĬ
    0.09
    è¿Ļ件äºĭ
    0.08
    äºĨä¸Ģ个
    0.08
    otre
    0.08
     Harley
    0.08
    Activations Density 0.003%

    No Known Activations