© 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. 11332
    Prev
    Next
    INDEX
    Explanations

    place names ending in ton

    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
    CAF
    -0.23
     overs
    -0.20
    _ABI
    -0.20
    棣
    -0.19
    示
    -0.19
    ergy
    -0.19
    ovi
    -0.18
    ãĤ¢ãĤ¦
    -0.18
     sanity
    -0.18
    Lord
    -0.18
    POSITIVE LOGITS
    èĨı
    0.21
    تÙĪÙĨ
    0.20
    .bias
    0.20
    edith
    0.19
    åľ¨ç¾İåĽ½
    0.19
    æ¯Ĵç´ł
    0.19
    tip
    0.19
    ÅĽl
    0.18
    translator
    0.18
     tip
    0.18
    Activations Density 0.014%

    No Known Activations