© 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. 41976
    Prev
    Next
    INDEX
    Explanations

    aspect ratio and scaling

    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
     Gul
    -0.07
     pur
    -0.07
    iben
    -0.07
    ocha
    -0.06
     thresholds
    -0.06
     fir
    -0.06
    .rm
    -0.06
    æ³Ľ
    -0.06
     perennial
    -0.06
    dia
    -0.06
    POSITIVE LOGITS
     ratio
    0.10
    ratio
    0.09
    æĶ¾å¤§
    0.09
     Ratio
    0.09
     ratios
    0.08
    åĢįæķ°
    0.08
    enseign
    0.08
    autos
    0.08
    AspectRatio
    0.08
    LOUR
    0.07
    Activations Density 0.001%

    No Known Activations