© 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. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 13808
    Prev
    Next
    INDEX
    Explanations

    quotation marks

    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
    ãĢĮ
    -0.28
     (
    -0.25
    “
    -0.25
    (
    -0.23
    -0.22
    ↵
    -0.21
    ãĢģ
    -0.20
     "
    -0.20
     m
    -0.20
    -0.19
    POSITIVE LOGITS
    /or
    0.33
    /OR
    0.24
     ÐŁÐ¾Ñĩем
    0.23
    phans
    0.23
    鸱
    0.23
    деÑĤ
    0.22
     tháºŃm
    0.20
    ucher
    0.19
    rey
    0.19
    zyst
    0.19
    Activations Density 0.062%

    No Known Activations