© 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. 49471
    Prev
    Next
    INDEX
    Explanations

    green and blue components

    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
    és
    -0.07
    æ¡Ī
    -0.07
    çī©çļĦ
    -0.07
    oid
    -0.06
    macher
    -0.06
    çĪ·
    -0.06
    iform
    -0.06
     Ehren
    -0.06
    æ¤
    -0.06
    ÑĦоÑĢм
    -0.06
    POSITIVE LOGITS
    _CONF
    0.09
     Istri
    0.07
    åį³å¢¨
    0.07
     kand
    0.07
    河山
    0.07
     puro
    0.07
    queda
    0.07
    /y
    0.07
    unno
    0.07
     pale
    0.07
    Activations Density 0.011%

    No Known Activations