© 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. 41424
    Prev
    Next
    INDEX
    Explanations

    conductive spinal cord

    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
    rach
    -0.07
    大äºĭ
    -0.07
     Downing
    -0.07
    æµ·å¸Ĥ
    -0.07
    æ¶ķ
    -0.07
    ä¹İ
    -0.06
    .layers
    -0.06
     TIN
    -0.06
    volu
    -0.06
    å²ģå²ģ
    -0.06
    POSITIVE LOGITS
    arez
    0.08
    æĦ¤
    0.08
    -send
    0.07
    xDF
    0.07
     커
    0.07
    åĴĮæķĻèĤ²
    0.07
    ãĥľãĥ¼
    0.07
    lian
    0.07
    zew
    0.07
    é¢ł
    0.07
    Activations Density 0.232%

    No Known Activations