© 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. 39832
    Prev
    Next
    INDEX
    Explanations

    acl, akil, acle, akon

    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
    ESC
    -0.08
    boss
    -0.07
    å°±æĭ¿
    -0.07
     Wiz
    -0.07
    èĤīçľ¼
    -0.07
     brod
    -0.07
    artil
    -0.07
    áĪĽ
    -0.07
    ioni
    -0.06
    )[:
    -0.06
    POSITIVE LOGITS
    acl
    0.08
    akil
    0.07
    iÄį
    0.07
    嬰
    0.07
    acle
    0.07
    akon
    0.07
    ertz
    0.07
    vvm
    0.07
    usul
    0.06
    åįģåħ«æĿ¡
    0.06
    Activations Density 0.001%

    No Known Activations