© 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. 33318
    Prev
    Next
    INDEX
    Explanations

    information structures and types

    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
    羽翼
    -0.07
     ê±°ëĵŃ
    -0.06
    igers
    -0.06
    شرÙĬÙĨ
    -0.06
    室åĨħ空æ°Ķ
    -0.06
    æIJŃä¸Ĭ
    -0.06
    å°½æĺ¯
    -0.06
     protector
    -0.06
    æ¥ļæ¥ļ
    -0.06
    _errno
    -0.06
    POSITIVE LOGITS
    psilon
    0.08
    å½¢
    0.07
    gradu
    0.07
    å¸ĥ伦
    0.07
    heil
    0.07
    伺
    0.07
    bill
    0.07
    ossal
    0.07
    otine
    0.07
    rotch
    0.07
    Activations Density 0.376%

    No Known Activations