© 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. 15527
    Prev
    Next
    INDEX
    Explanations

    deal in

    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
    ously
    -0.17
    OUS
    -0.17
    eous
    -0.17
    è¾Ī
    -0.16
    å«Į
    -0.15
    ecz
    -0.15
    ellen
    -0.15
    ous
    -0.15
    eer
    -0.15
    ï¸ı
    -0.15
    POSITIVE LOGITS
    tern
    0.22
    ness
    0.20
    locate
    0.20
    wyn
    0.18
    ç²ķ
    0.17
    ings
    0.17
    NESS
    0.16
    ystore
    0.16
    igned
    0.16
    thed
    0.16
    Activations Density 0.030%

    No Known Activations