© 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. 16462
    Prev
    Next
    INDEX
    Explanations

    titles of movies or works

    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
    onth
    -0.21
    atra
    -0.20
     oppos
    -0.19
    赦
    -0.19
    æķĪ
    -0.19
    奢ä¾Ī
    -0.19
    å¦ĤæĦı
    -0.18
    ãģ¨ãģª
    -0.18
     Mercy
    -0.17
    Front
    -0.17
    POSITIVE LOGITS
    MOTE
    0.20
    goal
    0.19
    ä¸ŃåĽ½åĪ¶éĢł
    0.19
    elts
    0.19
    vore
    0.19
    èĬŁ
    0.19
    pps
    0.18
    ieval
    0.18
    æĵį
    0.18
    åħ¨èĩªåĬ¨
    0.18
    Activations Density 0.004%

    No Known Activations