© 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. 22206
    Prev
    Next
    INDEX
    Explanations

    medal match

    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
    elan
    -0.07
    å°±éĢģ
    -0.07
    DEL
    -0.06
    ty
    -0.06
    æı£
    -0.06
     pretty
    -0.06
    OnChange
    -0.06
    é£ĺ
    -0.06
    é«ĺ人
    -0.06
    EX
    -0.06
    POSITIVE LOGITS
    ardown
    0.09
     opposite
    0.09
    ä¸ĢåºĶ
    0.08
    baliknya
    0.08
    å°ĩè»į
    0.08
     пÑĢоÑĤивополо
    0.08
    ä¸Ģ鸣
    0.08
    ymar
    0.08
    INI
    0.08
    oux
    0.08
    Activations Density 0.005%

    No Known Activations