© 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. 13151
    Prev
    Next
    INDEX
    Explanations

    https:// links and http

    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
    æ²»
    -0.21
    iph
    -0.20
    ut
    -0.18
    åİĭ
    -0.18
    èµ°
    -0.18
    And
    -0.18
    e
    -0.18
    åİĭè¿«
    -0.18
    âĸł
    -0.17
    str
    -0.17
    POSITIVE LOGITS
    (stdin
    0.22
    è¿Ļæĺ¯ä¸Ģ个
    0.22
    ä»ĭç´¹
    0.21
    ä»ĸæĺ¯ä¸Ģ个
    0.21
    _ComCallableWrapper
    0.20
    éĢĻæĺ¯
    0.20
    ÙħÙĨتدÙĬات
    0.20
    éĹ·
    0.19
    é«ĺçŃīéĻ¢æł¡
    0.19
    å¹²ä»Ģä¹Ī
    0.19
    Activations Density 1.042%

    No Known Activations