© 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. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 15181
    Prev
    Next
    INDEX
    Explanations

    quotes containing "yes" or "well"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-14b-saes/saes_Qwen_Qwen3-14B_batch_top_k/resid_post_layer_20
    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
     Ingram
    -0.20
    类似çļĦ
    -0.18
    æ¡¥
    -0.17
     Sext
    -0.17
    +-+-
    -0.16
     Narc
    -0.16
    hai
    -0.16
    _OPTS
    -0.16
    .addTo
    -0.16
     Gavin
    -0.16
    POSITIVE LOGITS
    ÑĭÑĪ
    0.18
    itag
    0.18
    gfx
    0.17
    à¸ĸ
    0.17
     StringComparison
    0.17
    .TryParse
    0.17
     leaning
    0.17
    éĶĻäºĨ
    0.17
    æ½ľ
    0.16
    ood
    0.16
    Activations Density 0.032%

    No Known Activations