© 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. 28836
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions or code endings

    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
    hattan
    -0.08
    landers
    -0.08
    enzio
    -0.08
    zinho
    -0.07
    oppi
    -0.07
    æ°ı
    -0.07
    zac
    -0.07
    пÑĤо
    -0.07
    eppe
    -0.07
    aat
    -0.07
    POSITIVE LOGITS
    ANS
    0.07
    rones
    0.07
    ans
    0.07
    idad
    0.06
     homogeneous
    0.06
     lyd
    0.06
    xon
    0.06
    å¤īåĮĸ
    0.06
    endig
    0.06
    ree
    0.06
    Activations Density 0.011%

    No Known Activations