© 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. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 55626
    Prev
    Next
    INDEX
    Explanations

    August, dates, or lists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    纤
    -0.08
    æijĺ
    -0.07
    æł
    -0.07
    åĪ»
    -0.07
    tical
    -0.07
    èĢĺ
    -0.06
    çºĸ
    -0.06
    ritten
    -0.06
    ëł´
    -0.06
    onger
    -0.06
    POSITIVE LOGITS
    åıįè¿ĩæĿ¥
    0.11
     already
    0.10
    å·²ç»ıæĺ¯
    0.09
    Already
    0.09
    å·²çĦ¶
    0.09
    å·²ç»ı
    0.08
    -after
    0.08
    already
    0.08
     Ñĥже
    0.08
    å·²ç»ıè¾¾åĪ°
    0.08
    Activations Density 0.317%

    No Known Activations