© 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. 40986
    Prev
    Next
    INDEX
    Explanations

    completed to admission

    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
    нÑĮ
    -0.07
    ums
    -0.07
    fad
    -0.07
    um
    -0.06
    æıIJæĹ©
    -0.06
    失
    -0.06
    ç¨įç¨į
    -0.06
     ergän
    -0.06
    emann
    -0.06
     goodness
    -0.06
    POSITIVE LOGITS
     usable
    0.13
    羣æŃ£æĦıä¹īä¸ĬçļĦ
    0.11
    inker
    0.11
    å®ŀéĻħ
    0.11
    羣æŃ£
    0.10
    å®ŀè´¨æĢ§
    0.10
    æľĢç»Ī
    0.10
     actual
    0.10
     полноÑĨен
    0.09
    å®ŀéĻħçļĦ
    0.09
    Activations Density 0.211%

    No Known Activations