© 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. 16888
    Prev
    Next
    INDEX
    Explanations

    copyright notice

    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
    --
    -0.18
    -looking
    -0.18
    -type
    -0.17
    ta
    -0.17
    讵
    -0.17
    ment
    -0.17
     latter
    -0.17
    gesch
    -0.16
    è·
    -0.16
    []
    -0.16
    POSITIVE LOGITS
    =-=-=-=-=-=-=-=-
    0.24
    /-
    0.19
    //-
    0.18
    åħ¼
    0.18
    sı
    0.18
    _-
    0.17
    éĩįçĤ¹é¢ĨåŁŁ
    0.17
    +-+-+-+-+-+-+-+-
    0.17
    0.16
    .obtain
    0.16
    Activations Density 0.396%

    No Known Activations