© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 42255
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    æĬ¥è®°èĢħ
    -0.08
     Filho
    -0.08
    á»ħu
    -0.07
    byter
    -0.07
    ...',
    -0.07
    panse
    -0.07
    úng
    -0.07
     Suas
    -0.07
    .objects
    -0.07
    (\$
    -0.07
    POSITIVE LOGITS
    è¡Įä¹ĭ
    0.07
    è¯Ħ
    0.07
    æıIJ
    0.07
    èĻ
    0.07
    è¯Ħå®ļ
    0.06
    )["
    0.06
    æĥŁæľī
    0.06
    iht
    0.06
    éĻį
    0.06
     incr
    0.06
    Activations Density 0.000%

    No Known Activations