© 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. 13810
    Prev
    Next
    INDEX
    Explanations

    Condell Park

    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
    trap
    -0.21
    InMillis
    -0.19
    cest
    -0.18
     rec
    -0.17
     Trio
    -0.17
    upil
    -0.17
    .shtml
    -0.17
    _secs
    -0.17
    odiac
    -0.17
    arring
    -0.17
    POSITIVE LOGITS
    _CONSTANT
    0.18
    неж
    0.18
    æĹ¶ä»£ä¸ŃåĽ½
    0.17
    æ³»
    0.17
    ç»Ī端
    0.16
    ä¸ĭéĿ¢å°ıç¼ĸ
    0.16
    çĺĺ
    0.16
    ç»İ
    0.16
    主æĦı
    0.16
    âĢ
    0.16
    Activations Density 0.009%

    No Known Activations