© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 57252
    Prev
    Next
    INDEX
    Explanations

    state machine descriptions

    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
     formatted
    -0.07
     Cad
    -0.07
    Cad
    -0.07
     Armen
    -0.07
    cad
    -0.07
    éĴīåŃIJ
    -0.06
    强åİ¿
    -0.06
    format
    -0.06
     cad
    -0.06
    åIJĪåIJĮ约å®ļ
    -0.06
    POSITIVE LOGITS
     reachable
    0.09
    æĮĸæİĺåħ¬åı¸
    0.08
    TextNode
    0.08
    èĢIJ
    0.08
    åħ¼æĢ»ç»ıçIJĨ
    0.08
     mappings
    0.07
    neau
    0.07
    ÄĥtÄĥ
    0.07
     Map
    0.07
    ủng
    0.07
    Activations Density 0.007%

    No Known Activations