© 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. 17437
    Prev
    Next
    INDEX
    Explanations

    .com or .so domains

    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
    umus
    -0.07
      ↵
    -0.07
     "(
    -0.06
    KE
    -0.06
    ÑĢи
    -0.06
    GO
    -0.06
     "$
    -0.06
    $$
    -0.06
     Cas
    -0.05
     "!
    -0.05
    POSITIVE LOGITS
    οÏįν
    0.09
    ¤íĮ
    0.08
    å·¥ä½ľåĬ¨æĢģ
    0.08
    reu
    0.08
    _checkpoint
    0.08
    ັ
    0.08
    –and
    0.08
    ólog
    0.08
    åħ®
    0.08
    bose
    0.07
    Activations Density 0.002%

    No Known Activations