© 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. 3656
    Prev
    Next
    INDEX
    Explanations

    code expression `exp`

    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
    æĢ¥äºĨ
    -0.09
    à®®à¯įப
    -0.07
    åĪºæ¿ĢæĢ§é£Łçī©
    -0.07
    اÙĦÙħÙĦ
    -0.07
    aven
    -0.07
    uy
    -0.07
    CLS
    -0.07
    .uml
    -0.07
    мÑı
    -0.07
    Mocks
    -0.07
    POSITIVE LOGITS
    odal
    0.07
    idah
    0.07
     Wrapper
    0.07
    éģĵçļĦ
    0.07
    彤
    0.06
    PAS
    0.06
    æIJŃ
    0.06
    egan
    0.06
    äºĪ
    0.06
    ANNER
    0.06
    Activations Density 0.032%

    No Known Activations