© 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. 47019
    Prev
    Next
    INDEX
    Explanations

    average, average, average, average

    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
    chini
    -0.07
    azī
    -0.07
    _MALLOC
    -0.07
    oraf
    -0.07
     vien
    -0.07
    æĺİçıł
    -0.06
     pana
    -0.06
    åIJ¸å¼ķæĽ´å¤ļçļĦ
    -0.06
    åIJĦæľī
    -0.06
     namedtuple
    -0.06
    POSITIVE LOGITS
    -average
    0.08
    .average
    0.08
    å¹³åĿĩåĢ¼
    0.08
    kers
    0.08
    稳
    0.08
     ensemble
    0.08
     avg
    0.07
    Ñīик
    0.07
    avg
    0.07
     average
    0.07
    Activations Density 0.002%

    No Known Activations