© 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. 41907
    Prev
    Next
    INDEX
    Explanations

    what's left, stand has, of nutritional, present invention

    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
    两年æĿ¥
    -0.07
    æľĢ常è§ģçļĦ
    -0.06
    ecd
    -0.06
     counting
    -0.06
     deb
    -0.06
    读åĩº
    -0.06
    èĨĺ
    -0.06
     short
    -0.06
     Cummings
    -0.06
    æ¸ħçĤ¹
    -0.06
    POSITIVE LOGITS
     Coverage
    0.09
    _coverage
    0.08
    -cover
    0.08
    fone
    0.08
    æĵ¬
    0.08
     coverage
    0.08
    -unstyled
    0.08
     getro
    0.08
    okka
    0.07
    зон
    0.07
    Activations Density 0.001%

    No Known Activations