© 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. 10878
    Prev
    Next
    INDEX
    Explanations

    construct, construction

    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
    ugin
    -0.09
    ª
    -0.08
    éĵĽ
    -0.08
    ÅĽrod
    -0.08
    ows
    -0.07
    ÏĢοÏĦε
    -0.07
    gnore
    -0.07
    venta
    -0.07
    ÑģÑĤÑĢ
    -0.07
    次çļĦ
    -0.07
    POSITIVE LOGITS
    ivist
    0.12
    ively
    0.11
    urally
    0.11
    OrUpdate
    0.10
     timeval
    0.10
    eur
    0.09
    ivism
    0.09
     ulang
    0.09
    ç»İ
    0.09
    enhagen
    0.09
    Activations Density 0.042%

    No Known Activations