© 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. 48109
    Prev
    Next
    INDEX
    Explanations

    0 degrees

    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
    ī¬
    -0.08
    ISTI
    -0.07
    istaa
    -0.07
    ª½
    -0.07
    ITTER
    -0.07
    ARRIER
    -0.07
    åºľçļĦ
    -0.07
    ARES
    -0.07
    ILLS
    -0.07
    YLE
    -0.06
    POSITIVE LOGITS
    Ñĥнк
    0.07
    çĤ¹éĴŁ
    0.07
    วัà¸Ĵ
    0.07
    ongyang
    0.07
    añ
    0.07
    uplic
    0.07
    unken
    0.07
    oto
    0.07
    ziej
    0.07
    ekor
    0.07
    Activations Density 0.021%

    No Known Activations