© 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. 57823
    Prev
    Next
    INDEX
    Explanations

    philosophical, ethical, moral, business, physics

    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
    ãģ¶ãĤĬ
    -0.08
    ä¸įå¦Ĥ
    -0.08
    oudre
    -0.07
    ToDevice
    -0.07
    Å¡te
    -0.07
    ademia
    -0.07
     непо
    -0.07
    WithPath
    -0.07
    ãģ¶
    -0.07
    arang
    -0.07
    POSITIVE LOGITS
    æĦıä¹īä¸Ĭ
    0.08
     principles
    0.08
    æĦıä¹īä¸ĬçļĦ
    0.07
    è§Ĵ度çľĭ
    0.07
    princip
    0.07
    è§Ĩè§Ĵ
    0.07
    å±±ä¸ĭ
    0.06
    è§Ĵ度æĿ¥çľĭ
    0.06
     perspective
    0.06
     standpoint
    0.06
    Activations Density 0.062%

    No Known Activations