© 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. 49886
    Prev
    Next
    INDEX
    Explanations

    mathematical definitions and formulas

    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
     Correa
    -0.08
     Generic
    -0.08
    .removeEventListener
    -0.07
    表çİ°åľ¨
    -0.07
    IDGET
    -0.07
    clone
    -0.07
    oreach
    -0.06
    egie
    -0.06
    _generic
    -0.06
    ucci
    -0.06
    POSITIVE LOGITS
    å®ļä¹ī
    0.13
    å®ļä¹ī为
    0.13
     definitions
    0.12
     definition
    0.11
    å®ļ義
    0.11
    .define
    0.11
     Definitions
    0.11
    -definition
    0.10
    å®ļä¹īçļĦ
    0.10
    å®ļä¹īäºĨ
    0.10
    Activations Density 0.050%

    No Known Activations