© 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. 34324
    Prev
    Next
    INDEX
    Explanations

    Greek letters with parameters

    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
    -0.07
     Sang
    -0.06
    uce
    -0.06
    anto
    -0.06
    ottage
    -0.06
     Sep
    -0.06
     -
    -0.05
    idia
    -0.05
     (
    -0.05
     [
    -0.05
    POSITIVE LOGITS
    èħ¹
    0.08
     mily
    0.08
    ç±ģ
    0.08
    éħĴå±ĭ
    0.08
    /Gate
    0.08
    teness
    0.08
     Cly
    0.08
    ẩn
    0.08
    iless
    0.08
    ì°¬
    0.08
    Activations Density 0.007%

    No Known Activations