© 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. 29041
    Prev
    Next
    INDEX
    Explanations

    closing parentheses or quotes

    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
     Kep
    -0.08
    ollo
    -0.07
    缸åħ³æݨèįIJ
    -0.07
    精工
    -0.07
    ÏĦÏģι
    -0.07
     unwrap
    -0.07
    æ±Ĥè´Ń
    -0.07
     "::
    -0.06
    orest
    -0.06
    大修
    -0.06
    POSITIVE LOGITS
    lemen
    0.07
    <|box_end|>
    0.07
    IGA
    0.07
    ilot
    0.07
    çĭĤ
    0.06
     assemb
    0.06
    åĨ
    0.06
    £¼
    0.06
    icch
    0.06
    ÃŃg
    0.06
    Activations Density 0.270%

    No Known Activations