© 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. 43288
    Prev
    Next
    INDEX
    Explanations

    accessories and gear

    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
    è¿Ļæľ¬
    -0.07
     Fried
    -0.07
    æĥľ
    -0.06
    åıijæĮ¥
    -0.06
    .har
    -0.06
    ÑĤаж
    -0.06
    ozo
    -0.06
    ä¹ĭ书
    -0.06
    èµ
    -0.06
    åĪĨä¹ĭ
    -0.06
    POSITIVE LOGITS
    åıĬéħįå¥Ĺ
    0.08
    æ¥ŃåĭĻ
    0.08
    WithValue
    0.08
    åĿıçļĦ
    0.08
     adaptable
    0.08
    WithError
    0.08
    WithPath
    0.08
     adopts
    0.08
    wchar
    0.08
     tém
    0.08
    Activations Density 0.698%

    No Known Activations