© 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. 13267
    Prev
    Next
    INDEX
    Explanations

    assembly, distribution, revision

    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
     sext
    -0.18
    æĿµ
    -0.18
     epis
    -0.18
    .Drawable
    -0.18
    ief
    -0.18
    -Sah
    -0.18
    æĬĬ她
    -0.18
    .Dom
    -0.18
    asu
    -0.17
    å¨ij
    -0.17
    POSITIVE LOGITS
    Revision
    0.20
    åľ»
    0.19
    æĦŁæĥħ
    0.19
    _pieces
    0.19
     MODIFY
    0.19
    ucc
    0.18
    槿
    0.18
    诸èijĽ
    0.18
    há»ķ
    0.18
    speaker
    0.18
    Activations Density 0.003%

    No Known Activations