© 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. 56124
    Prev
    Next
    INDEX
    Explanations

    behavior across contexts

    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
    åłĤçļĩ
    -0.08
    পà§ģর
    -0.08
    ifiable
    -0.08
    ified
    -0.08
    ¹
    -0.08
    itial
    -0.08
    ifier
    -0.07
     whence
    -0.07
     lá»ĵ
    -0.07
    å¶
    -0.07
    POSITIVE LOGITS
    举æŃ¢
    0.13
    weisen
    0.10
    /function
    0.09
    dez
    0.08
    acons
    0.08
    yst
    0.08
    èºı
    0.08
    avior
    0.08
     behavior
    0.07
    behavior
    0.07
    Activations Density 0.041%

    No Known Activations