© 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. 63415
    Prev
    Next
    INDEX
    Explanations

    null, visible, nothing

    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
     apt
    -0.07
    quine
    -0.07
    ÚĨÙĩ
    -0.07
    uch
    -0.07
    ogle
    -0.07
     Renn
    -0.06
    «
    -0.06
    pole
    -0.06
    ATHER
    -0.06
    åIJĽå®ī
    -0.06
    POSITIVE LOGITS
     except
    0.09
     outside
    0.08
    Except
    0.08
    ç´¯
    0.08
    å¿Ļ
    0.08
     elsewhere
    0.08
    éĻ¤éĿŀ
    0.08
     Except
    0.08
    éĤ£äºĽäºº
    0.08
    igu
    0.08
    Activations Density 0.008%

    No Known Activations