© 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. 40488
    Prev
    Next
    INDEX
    Explanations

    literals or constants

    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
    icer
    -0.08
    azier
    -0.07
     $__
    -0.07
    éĿ¢æĹł
    -0.07
    _hooks
    -0.07
    .inverse
    -0.07
    ournals
    -0.07
    yre
    -0.07
    é¢ĦæµĭæĬ¥åijĬ
    -0.07
    æ¯ıåĪ°
    -0.07
    POSITIVE LOGITS
    常éĩı
    0.10
     hardcoded
    0.10
     predefined
    0.08
    _constant
    0.08
     constants
    0.08
    constant
    0.08
     constant
    0.08
    _LITERAL
    0.08
    示ä¾ĭ
    0.07
     constantes
    0.07
    Activations Density 0.376%

    No Known Activations