© 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. 50647
    Prev
    Next
    INDEX
    Explanations

    CH structures

    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
    :M
    -0.07
    erve
    -0.06
    ers
    -0.06
    äºı
    -0.06
    :\\
    -0.06
    é¢ĺ
    -0.06
    oral
    -0.06
    容
    -0.06
    ÙĩÙĨ
    -0.06
    emean
    -0.06
    POSITIVE LOGITS
    idor
    0.09
    ä¹ĭæľ¯
    0.08
    ippi
    0.08
    epam
    0.08
    icke
    0.08
    çļĦ主è¦ģéĹ®é¢ĺ
    0.08
    èĸ¬å±Ģ
    0.08
    _cid
    0.08
    antium
    0.07
    AGEN
    0.07
    Activations Density 0.004%

    No Known Activations