© 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. 24835
    Prev
    Next
    INDEX
    Explanations

    unit of length or 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
     Pilk
    -0.09
    cze
    -0.08
    illage
    -0.08
    à¤Łà¤ķ
    -0.08
    ccount
    -0.08
    áīµ
    -0.08
     Dispos
    -0.08
    åįĥçĵ¦
    -0.08
    å¼Ģæĭį
    -0.08
     Galli
    -0.08
    POSITIVE LOGITS
    é£İ鼨
    0.06
    ä¸Ī
    0.06
    åŁº
    0.06
    æĿIJ
    0.06
    ılar
    0.06
     Χ
    0.06
     X
    0.06
    вÑĸд
    0.05
    ÑĤан
    0.05
     physical
    0.05
    Activations Density 0.117%

    No Known Activations