© 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. 13636
    Prev
    Next
    INDEX
    Explanations

    balsamic

    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
    theless
    -0.20
    ites
    -0.19
    ÃŃcia
    -0.19
    éĻIJãĤĬ
    -0.18
    antha
    -0.18
    lain
    -0.18
    裳
    -0.17
    椽
    -0.17
    ITES
    -0.17
    æľªæĪIJ
    -0.17
    POSITIVE LOGITS
    desk
    0.23
    y
    0.19
    nable
    0.19
    wick
    0.19
    ez
    0.19
    sch
    0.17
    yl
    0.17
    æİĸ
    0.17
    san
    0.16
    sun
    0.16
    Activations Density 0.019%

    No Known Activations