© 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. 63687
    Prev
    Next
    INDEX
    Explanations

    simplex optimization programs

    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
    yms
    -0.08
    alue
    -0.07
    ä¿¡æģ¯ä¸İ
    -0.07
    soles
    -0.07
    ivating
    -0.07
    åīįç¨ĭ
    -0.07
    竹æŀĹ
    -0.07
    两åѦä¸Ģåģļ
    -0.07
    并å¤Ħ
    -0.06
    aip
    -0.06
    POSITIVE LOGITS
    DECL
    0.07
    RARY
    0.07
    ijen
    0.07
    ÑĹ
    0.07
     ë°©
    0.07
    +-+-
    0.07
    ¾
    0.06
     помÑĸ
    0.06
    icch
    0.06
    é¼»
    0.06
    Activations Density 0.003%

    No Known Activations