© 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. 50018
    Prev
    Next
    INDEX
    Explanations

    assign to values

    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
     Ejem
    -0.09
    ë°¥
    -0.09
    ìį¨
    -0.08
     IncluÃŃdos
    -0.08
    quist
    -0.08
    illot
    -0.08
    geist
    -0.08
    gend
    -0.08
    strate
    -0.08
    wards
    -0.08
    POSITIVE LOGITS
    ments
    0.12
    a
    0.08
    (assign
    0.08
    ively
    0.08
    MENT
    0.07
    ات
    0.07
    ä¸ĵäººè´Łè´£
    0.07
    ss
    0.07
    ally
    0.07
     ulang
    0.07
    Activations Density 0.041%

    No Known Activations