© 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. 16874
    Prev
    Next
    INDEX
    Explanations

    Calibre, book, challenge, about, reviews

    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
    éĻĤ
    -0.20
    ãģ°ãģĭãĤĬ
    -0.20
    ä¿ĿçķĻ
    -0.19
    渺
    -0.19
    çħĮ
    -0.18
    çľĩ
    -0.18
    åį¢
    -0.18
    ç¾½
    -0.18
     Donna
    -0.17
     sill
    -0.17
    POSITIVE LOGITS
    /facebook
    0.20
    幡
    0.20
    .community
    0.20
    读书
    0.19
    list
    0.19
    æīĵåį¡
    0.19
    .comm
    0.18
    azzi
    0.18
    ä¿®åħ»
    0.18
    ç®Ĺ
    0.18
    Activations Density 0.004%

    No Known Activations