© 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. 25208
    Prev
    Next
    INDEX
    Explanations

    disposed, articulated, guided, attached, interconnected

    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
    caff
    -0.08
     wavelengths
    -0.07
     intens
    -0.07
    åį·ç§¯
    -0.07
    patch
    -0.07
    oku
    -0.06
    åģľæľº
    -0.06
     diga
    -0.06
    åĢĴéľī
    -0.06
    ä¸Ģæ³¢
    -0.06
    POSITIVE LOGITS
     freely
    0.12
    èĩªçĶ±çļĦ
    0.11
    åı¯ä»¥èĩªçĶ±
    0.11
    æ»ij
    0.11
    èĩªçĶ±ãģ«
    0.11
    åħģ许çļĦ
    0.11
     movement
    0.11
    åħģ许
    0.10
    Movement
    0.10
    movement
    0.10
    Activations Density 0.084%

    No Known Activations