© 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. 47224
    Prev
    Next
    INDEX
    Explanations

    boundary or endpoints

    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
    éĢļè¿ĩ使çĶ¨
    -0.09
    _ONCE
    -0.08
    iewicz
    -0.08
    ainers
    -0.08
    Streamer
    -0.07
    XYZ
    -0.07
    é¦Ĩéķ¿
    -0.07
    æıĽãģĪ
    -0.07
    erek
    -0.07
    æĬ½è±¡
    -0.07
    POSITIVE LOGITS
    éĢĢåĮĸ
    0.07
    ãĤ³ãĥ¼
    0.07
    æķŀ
    0.07
    deg
    0.07
    éĢĢ
    0.07
    è°·åºķ
    0.07
    çŀ©
    0.06
     endpoints
    0.06
    side
    0.06
     side
    0.06
    Activations Density 0.002%

    No Known Activations