© 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. 3447
    Prev
    Next
    INDEX
    Explanations

    neural tube / gray matter / irritable bowel

    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
    åŃĺ
    -0.07
    isma
    -0.07
    ouston
    -0.07
    adak
    -0.07
    对åįİ
    -0.06
     foregoing
    -0.06
    omis
    -0.06
    iped
    -0.06
    efined
    -0.06
    bard
    -0.06
    POSITIVE LOGITS
    sworth
    0.08
    fors
    0.08
    éĿ¡
    0.07
    åħ¬ä¼Ĺå¹³åı°
    0.07
    æ´²éĻħ
    0.07
    路人
    0.07
    ä¹IJ天
    0.07
     gê
    0.07
    øj
    0.07
    Formatter
    0.07
    Activations Density 0.302%

    No Known Activations