© 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. 43151
    Prev
    Next
    INDEX
    Explanations

    journal citations and years

    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
    æįIJ
    -0.07
    建ç«ĭåľ¨
    -0.07
    罪
    -0.07
    olib
    -0.07
    èĩ
    -0.07
    angelog
    -0.07
    åŀĤ
    -0.07
    ÑİÑĢ
    -0.07
    罪çļĦ
    -0.07
     gol
    -0.07
    POSITIVE LOGITS
    å°ijæķ°
    0.07
    ôi
    0.07
    éal
    0.07
    娲
    0.07
    åĭ¿æī°
    0.07
    ubu
    0.07
    éĤ£æŶçļĦ
    0.07
    å¼Ħ
    0.06
    _ALWAYS
    0.06
    éĤ£æŶåĢĻ
    0.06
    Activations Density 0.053%

    No Known Activations