© 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. 18531
    Prev
    Next
    INDEX
    Explanations

    logic model

    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
    OrUpdate
    -0.09
    pero
    -0.08
    Åijl
    -0.07
    ments
    -0.07
    semble
    -0.07
    orrow
    -0.07
    олÑĮ
    -0.07
    ikel
    -0.07
    ì§ķ
    -0.07
    eker
    -0.07
    POSITIVE LOGITS
    ALLY
    0.09
    ä¸Ĭ讲
    0.09
    -speaking
    0.08
    ally
    0.08
    raft
    0.08
    æݨçIJĨ
    0.08
    /math
    0.08
    ä¸įéĢļ
    0.07
    amente
    0.07
    wijs
    0.07
    Activations Density 0.010%

    No Known Activations