© 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. 3351
    Prev
    Next
    INDEX
    Explanations

    continuous variable, time, or observation

    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
    åĿļæ¯ħ
    -0.08
    assy
    -0.08
    åĤ²
    -0.08
     uncomp
    -0.07
    åĢĶ
    -0.07
    VRT
    -0.07
    æ®ĭ
    -0.07
    veren
    -0.07
    赫赫
    -0.07
    stad
    -0.07
    POSITIVE LOGITS
     continuous
    0.16
    continuous
    0.15
    Continuous
    0.15
     Continuous
    0.15
     непÑĢеÑĢÑĭв
    0.15
     continuum
    0.14
    è¿ŀç»Ń
    0.14
     continuously
    0.12
     continua
    0.12
    _continuous
    0.12
    Activations Density 0.157%

    No Known Activations