© 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. 31423
    Prev
    Next
    INDEX
    Explanations

    writer, singer, cartoonist, poet

    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
    æĮ¨
    -0.08
    éĢłçī©
    -0.07
    åħ¨æĸ¹ä½įçļĦ
    -0.07
     Beh
    -0.07
    èĪªç©º
    -0.06
    å¤§æľ¬
    -0.06
    /security
    -0.06
    .ribbon
    -0.06
    ilangan
    -0.06
     ageing
    -0.06
    POSITIVE LOGITS
    å½¢å¼ıå¤ļæł·
    0.09
    ä½ĵè£ģ
    0.08
    åĴĮè§Ĩé¢ij
    0.08
     format
    0.08
    BuilderFactory
    0.08
    两大类
    0.08
    é£İæł¼
    0.08
    ä¸ĢæŀĿ
    0.08
    è¿ħéĢŁåıijå±ķ
    0.08
    ä¸Ģç±»
    0.07
    Activations Density 0.027%

    No Known Activations