© 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. 65164
    Prev
    Next
    INDEX
    Explanations

    Software or site

    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
    ä¸Ģçķª
    -0.07
    idler
    -0.07
    ovid
    -0.07
    shint
    -0.06
    าà¸Ķ
    -0.06
    ืà¸Ļ
    -0.06
    rico
    -0.06
    ellet
    -0.06
    able
    -0.06
    Ñĸй
    -0.06
    POSITIVE LOGITS
    ificent
    0.07
    éĢĬ
    0.07
    åģļ好äºĭ
    0.07
    cope
    0.07
    è¡Į家
    0.07
    å¦ĤæľŁ
    0.07
    eltas
    0.07
    å®¢æľº
    0.07
    å°Ķåħĭ
    0.07
    haften
    0.06
    Activations Density 0.035%

    No Known Activations