© 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. 57293
    Prev
    Next
    INDEX
    Explanations

    shown followed by 'at', 'here', 'below', 'in', 'to', 'covers'

    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
    ãģĵãģ¨
    -0.11
    ters
    -0.11
    gid
    -0.10
    ми
    -0.10
    mino
    -0.10
    ë¡Ń
    -0.09
    plier
    -0.09
    mlin
    -0.09
    ering
    -0.09
    eenth
    -0.09
    POSITIVE LOGITS
     dolayı
    0.10
    igli
    0.10
    ledge
    0.10
    alysis
    0.09
    etwork
    0.08
    禺
    0.08
    mers
    0.08
    iders
    0.08
    ìľ¼ë¡ľ
    0.08
    ยา
    0.08
    Activations Density 0.029%

    No Known Activations