© 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. 46172
    Prev
    Next
    INDEX
    Explanations

    date and time stamps

    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
    é¦ĸéķ¿
    -0.08
    åħĪåľ¨
    -0.07
    ench
    -0.07
    ushman
    -0.07
    缴éĢļ
    -0.07
    lbrace
    -0.07
    Lean
    -0.07
     Zaj
    -0.07
     pon
    -0.07
    REDIT
    -0.07
    POSITIVE LOGITS
    iri
    0.07
    iele
    0.07
    OLA
    0.07
    olem
    0.06
    rawer
    0.06
    ola
    0.06
    ienze
    0.06
    Forms
    0.06
    nton
    0.06
    大åı¯
    0.06
    Activations Density 0.299%

    No Known Activations