© 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. 28173
    Prev
    Next
    INDEX
    Explanations

    scientific and technical terms

    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
    /browse
    -0.07
     ratio
    -0.07
     Ratio
    -0.07
    andr
    -0.07
     ratios
    -0.07
    å±±æĿij
    -0.07
    沿éĢĶ
    -0.06
    ratio
    -0.06
    æ±²
    -0.06
    Ratio
    -0.06
    POSITIVE LOGITS
    ubar
    0.08
    ulte
    0.08
    éĢŁåº¦
    0.08
     velocidad
    0.08
    Interval
    0.08
    çļĦéĢŁåº¦
    0.08
    åħ·ä½ĵæŶéĹ´
    0.08
    ifestyles
    0.08
    åIJĮå·¥
    0.08
    elocity
    0.08
    Activations Density 0.019%

    No Known Activations