© 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. 2619
    Prev
    Next
    INDEX
    Explanations

    View this, Show More, View Gallery

    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
    plevel
    -0.09
    uarios
    -0.08
    urtle
    -0.07
    anness
    -0.07
    ÑĤеÑĢапев
    -0.07
    ktop
    -0.07
    ê¹IJ
    -0.07
    arness
    -0.07
    ductive
    -0.07
    insatz
    -0.07
    POSITIVE LOGITS
    etheless
    0.07
     Lain
    0.07
     Aside
    0.06
     Falk
    0.06
    re
    0.06
    íĶ½
    0.06
    jee
    0.06
    %\
    0.06
    ä¸ºæľŁ
    0.06
    blas
    0.06
    Activations Density 0.010%

    No Known Activations