© 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. 23783
    Prev
    Next
    INDEX
    Explanations

    new types of

    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¿ĻäºĽä¸ľè¥¿
    -0.09
    ulte
    -0.07
    该åĨħ容
    -0.07
    alda
    -0.07
    áºŃy
    -0.07
    urgia
    -0.07
    ceeded
    -0.07
    mania
    -0.07
    assis
    -0.07
    çĤ¯
    -0.07
    POSITIVE LOGITS
     ones
    0.11
    ç±»åŀĭ
    0.10
     types
    0.10
     jenis
    0.10
    Types
    0.09
    çļĦç±»åŀĭ
    0.09
     Types
    0.09
     tipos
    0.08
    ä¹ĭåĪĨ
    0.08
    é¡ŀåŀĭ
    0.08
    Activations Density 0.626%

    No Known Activations