© 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. 40417
    Prev
    Next
    INDEX
    Explanations

    study was

    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
    ysten
    -0.08
    ÐŃÐļ
    -0.08
    tori
    -0.08
     }(
    -0.08
    pcf
    -0.07
    ncy
    -0.07
    è§Ĩç½ij
    -0.07
    idente
    -0.07
     intelig
    -0.07
    ONY
    -0.07
    POSITIVE LOGITS
    缸è¾ħ
    0.07
    Facing
    0.06
    èĤī
    0.06
    AJ
    0.06
     Facing
    0.06
    amp
    0.06
    æ¡¥
    0.06
    uras
    0.06
    以èĩ³
    0.06
    DT
    0.06
    Activations Density 0.563%

    No Known Activations