© 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. 21835
    Prev
    Next
    INDEX
    Explanations

    SQL bind fields

    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
    ffel
    -0.07
    飬
    -0.07
    ough
    -0.07
     ÑĤеÑħниÑĩеÑģкой
    -0.07
    issy
    -0.07
    chat
    -0.07
    imler
    -0.07
    stral
    -0.07
    -chat
    -0.07
    kl
    -0.07
    POSITIVE LOGITS
     âĢ¦
    0.10
     [âĢ¦]
    0.08
    [âĢ¦]
    0.08
     [...]
    0.08
    (...)
    0.07
    [...]
    0.07
    âĢij
    0.07
     [âĢ¦
    0.07
    _*
    0.07
     (âĢ¦)
    0.07
    Activations Density 0.257%

    No Known Activations