© 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. 49757
    Prev
    Next
    INDEX
    Explanations

    fractions with slashes

    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
    forgettable
    -0.07
    çĪ±èĩªå·±
    -0.07
    ugas
    -0.07
    òng
    -0.06
    æ±°
    -0.06
    inki
    -0.06
    ä¸ĩåħĥ以ä¸Ĭ
    -0.06
     Rubin
    -0.06
    _MPI
    -0.06
    ↵        ↵        ↵
    -0.06
    POSITIVE LOGITS
    æķ´
    0.08
    assar
    0.07
    _written
    0.07
    æł¼
    0.07
    åĢį
    0.07
     written
    0.07
    /original
    0.07
    -original
    0.07
    omic
    0.07
    .valueOf
    0.07
    Activations Density 0.001%

    No Known Activations