© 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. 14306
    Prev
    Next
    INDEX
    Explanations

    spectroscopy measurements

    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
    ç¹ģä½ĵ
    -0.07
    ç¹ģ
    -0.07
    åªĴä»ĭ
    -0.06
     Entw
    -0.06
     alternatives
    -0.06
    urse
    -0.06
     decking
    -0.06
    æĻĴ
    -0.06
    osis
    -0.06
     outdated
    -0.06
    POSITIVE LOGITS
    鬼çİĭ
    0.08
    agerie
    0.08
     disappearance
    0.08
    itta
    0.08
    çĪ±è½¦
    0.07
    ÅĤow
    0.07
    èµ·åĪĿ
    0.07
    ammer
    0.07
     morphology
    0.07
    åĻ¨ä»¶
    0.07
    Activations Density 0.257%

    No Known Activations