© 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. 8780
    Prev
    Next
    INDEX
    Explanations

    credit, photograph, or attribution

    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
    è¿ĩä¸Ģ个
    -0.09
    غÙĪ
    -0.08
    رÙĪÛĮ
    -0.08
    eo
    -0.08
    é«ĺé«ĺçļĦ
    -0.07
    зон
    -0.07
    ELTS
    -0.07
    ick
    -0.07
    hoe
    -0.07
    _undo
    -0.07
    POSITIVE LOGITS
    ponsive
    0.06
    ç¿
    0.06
    stellen
    0.06
    lah
    0.06
    shed
    0.06
    ÙĤاÙĤ
    0.06
    ÅĻi
    0.06
     foll
    0.06
     SOP
    0.06
     anticip
    0.06
    Activations Density 0.004%

    No Known Activations