© 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. 42998
    Prev
    Next
    INDEX
    Explanations

    programming code elements

    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
    #{@
    -0.08
    满洲
    -0.07
    éĺħè¯»æľ¬æĸĩåīį
    -0.07
    æīĭéĩĮçļĦ
    -0.07
    <html
    -0.07
    igan
    -0.07
    æľºçŃī
    -0.07
    elius
    -0.07
    项è§Ħå®ļ
    -0.07
    sted
    -0.07
    POSITIVE LOGITS
    olet
    0.06
    åľ¨æīĢ
    0.06
    dik
    0.06
    èĢģçīĮ
    0.06
    ucc
    0.06
    uida
    0.06
    æ½ľ
    0.06
    otte
    0.06
     ket
    0.06
    hone
    0.06
    Activations Density 0.267%

    No Known Activations