© 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. 24089
    Prev
    Next
    INDEX
    Explanations

    variable types and declarations

    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
    akers
    -0.07
    imson
    -0.07
    ure
    -0.07
    /cpp
    -0.07
    åı°æµ·
    -0.07
    éĶĭ
    -0.07
    宣
    -0.07
    cule
    -0.07
    èıħ
    -0.07
    ä¸ŃçıŃ
    -0.06
    POSITIVE LOGITS
    Ranked
    0.07
    ä¸įåıĬ
    0.07
    æĤī
    0.07
    .cy
    0.07
    庶
    0.07
    _wr
    0.07
    _PAYLOAD
    0.06
    é«ĺèĢĥæĪIJ绩
    0.06
    desired
    0.06
    uz
    0.06
    Activations Density 0.007%

    No Known Activations