© 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. 23715
    Prev
    Next
    INDEX
    Explanations

    golden hour

    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
    çī¹åĪ«æĺ¯å¯¹
    -0.06
    uper
    -0.06
    -m
    -0.06
    è¯Ńè¨Ģ表达
    -0.06
    ä»¿ä½Ľåľ¨
    -0.06
    大éŨ
    -0.06
    elang
    -0.06
    eringen
    -0.06
    è¯Ńè¨ĢæĸĩåŃĹ
    -0.06
    ipur
    -0.06
    POSITIVE LOGITS
    ãģ¨ãĤĤ
    0.08
    ä¹Łåı«
    0.08
    ä¹Łç§°
    0.08
    )":
    0.08
    ikov
    0.08
    æŁ³
    0.07
    νη
    0.07
    ãģ¨ãĤĤè¨Ģ
    0.07
     genannt
    0.07
    ä¹Łç§°ä¸º
    0.07
    Activations Density 0.245%

    No Known Activations