© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 2865
    Prev
    Next
    INDEX
    Explanations

    clinically relevant

    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
    llib
    -0.07
    gte
    -0.07
    pch
    -0.06
    anner
    -0.06
    lico
    -0.06
    ovac
    -0.06
    ä¹Łåı¯ä»¥ä½¿çĶ¨
    -0.06
    éķij
    -0.06
    ä¸į幸
    -0.06
     Pace
    -0.06
    POSITIVE LOGITS
    ä¹Łåıªæľī
    0.13
    åıªæľī
    0.13
     only
    0.12
    åıªæľīéĢļè¿ĩ
    0.11
     Only
    0.11
    only
    0.10
    åĶ¯æľī
    0.10
    åıªæľīåľ¨
    0.10
     ÙģÙĤØ·
    0.10
    Only
    0.10
    Activations Density 0.060%

    No Known Activations