© 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. 30758
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions with variables and operators

    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
    efa
    -0.07
    oyer
    -0.07
    mast
    -0.07
    åıĤè®Ń
    -0.07
    amm
    -0.06
    ùi
    -0.06
    &m
    -0.06
    vd
    -0.06
    &E
    -0.06
    åı¦å¤ĸä¸Ģ个
    -0.06
    POSITIVE LOGITS
    atico
    0.07
    atica
    0.07
    çī
    0.07
    _RESOURCES
    0.07
    athering
    0.07
     اÙĦÙĪا
    0.07
    åħ°çī¹
    0.07
    带åĽŀ家
    0.07
    为大家带æĿ¥
    0.07
    angsa
    0.07
    Activations Density 0.016%

    No Known Activations