© 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. 7320
    Prev
    Next
    INDEX
    Explanations

    identity operator, joys, day

    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
    Rol
    -0.07
    ä¸Ģæī¹
    -0.07
    ne
    -0.07
    vei
    -0.06
    æĸ°åĬłåĿ¡
    -0.06
     interp
    -0.06
    ÙĨب
    -0.06
    èĢģæĮĿ
    -0.06
     Shapiro
    -0.06
     escap
    -0.06
    POSITIVE LOGITS
     Www
    0.08
     representing
    0.08
    代表
    0.08
    代表çĿĢ
    0.08
    代表äºĨ
    0.07
    à¸ģว
    0.07
    _repr
    0.07
    åıªä»£è¡¨
    0.07
    zeÅĽ
    0.07
    ặm
    0.07
    Activations Density 0.003%

    No Known Activations