© 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. 20967
    Prev
    Next
    INDEX
    Explanations

    invention relates to

    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
    æŀķ
    -0.07
    osz
    -0.07
    é¾Ħ
    -0.07
    å¿ħé¡»
    -0.06
    Creation
    -0.06
    idd
    -0.06
     literally
    -0.06
    ook
    -0.06
    人大
    -0.06
    onom
    -0.06
    POSITIVE LOGITS
    _FRAMEBUFFER
    0.09
     exti
    0.08
    ’**
    0.08
    extensions
    0.08
     extensions
    0.08
     extensión
    0.08
     extend
    0.08
    extend
    0.08
    atk
    0.08
    Extend
    0.08
    Activations Density 0.066%

    No Known Activations