© 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. 16076
    Prev
    Next
    INDEX
    Explanations

    numbers and measurement symbols

    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
    raq
    -0.06
    åı¯è¯»
    -0.06
    ä¸ĢæıIJ
    -0.06
    ase
    -0.06
    ET
    -0.06
    .readString
    -0.06
    \\.
    -0.06
    /pm
    -0.06
    anal
    -0.05
    ask
    -0.05
    POSITIVE LOGITS
    ezo
    0.08
    inten
    0.08
    iken
    0.08
    ç¾ļ
    0.08
     Intercept
    0.08
    ãĤĵ
    0.08
    ultz
    0.08
     consts
    0.08
    aray
    0.08
    inach
    0.07
    Activations Density 0.001%

    No Known Activations