© 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. 63691
    Prev
    Next
    INDEX
    Explanations

    AI models and chatbots

    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
     ke
    -0.07
    _scheme
    -0.07
    .bmp
    -0.07
    转载èĩ³
    -0.07
    .xhtml
    -0.07
    raid
    -0.07
    æīĭ游ç½ij
    -0.07
     counted
    -0.07
    _transport
    -0.07
    åį«è®¡å§Ķ
    -0.07
    POSITIVE LOGITS
     chat
    0.10
    Chat
    0.10
     Chat
    0.09
     halluc
    0.09
    (Chat
    0.09
    /chat
    0.09
     prompts
    0.09
     outputs
    0.09
    .ai
    0.09
    -chat
    0.08
    Activations Density 0.063%

    No Known Activations