© 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. 12193
    Prev
    Next
    INDEX
    Explanations

    fractal dimension

    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
    aton
    -0.08
    æĹłåıį
    -0.08
     singkat
    -0.07
    大å°ĨåĨĽ
    -0.07
    adero
    -0.07
     вÑģпом
    -0.07
    attu
    -0.07
    ÑĦаÑĢ
    -0.07
     Conj
    -0.07
    è¾ħæĸĻ
    -0.07
    POSITIVE LOGITS
     fract
    0.11
    actal
    0.09
     scaling
    0.08
     Scaling
    0.08
    recursive
    0.08
    Scaling
    0.08
     Zäh
    0.08
    æĮĩæķ°
    0.08
     recursively
    0.08
     logarith
    0.08
    Activations Density 0.030%

    No Known Activations