© 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. 10392
    Prev
    Next
    INDEX
    Explanations

    names and numerical identifiers

    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
    gres
    -0.07
    arest
    -0.07
    Accessor
    -0.07
     بط
    -0.06
    undler
    -0.06
    硬
    -0.06
     bog
    -0.06
    spro
    -0.06
    èĻļ
    -0.06
    chend
    -0.06
    POSITIVE LOGITS
     canh
    0.08
    _descriptor
    0.08
    æ±°
    0.07
    à·Ķà·Ģ
    0.07
    ahan
    0.07
    pei
    0.07
    oui
    0.07
     ego
    0.07
     Descriptor
    0.07
    oman
    0.07
    Activations Density 0.150%

    No Known Activations