© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 48697
    Prev
    Next
    INDEX
    Explanations

    heavens and earth

    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
    iah
    -0.08
    elah
    -0.08
     “âĢ¦
    -0.07
     *âĢŀ
    -0.07
    ",{
    -0.07
    ادر
    -0.07
    arkin
    -0.07
     "...
    -0.07
    _DAT
    -0.07
    aska
    -0.07
    POSITIVE LOGITS
     [
    0.07
     Participant
    0.07
    esture
    0.07
    è¥Ħ
    0.07
     speculative
    0.06
    Participant
    0.06
    äºīåħī
    0.06
     af
    0.06
    ене
    0.06
    对æīĢ
    0.06
    Activations Density 0.050%

    No Known Activations