© 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. 51218
    Prev
    Next
    INDEX
    Explanations

    as published

    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
    аем
    -0.08
    lessly
    -0.07
    ãģªãģĮãĤī
    -0.07
    à¸ģวà¹Īา
    -0.07
    ollywood
    -0.07
    ķ
    -0.07
    ä¹ĭ家
    -0.07
    kony
    -0.07
    «
    -0.07
    éĵ¿
    -0.07
    POSITIVE LOGITS
    sembl
    0.15
    cribed
    0.15
    paragus
    0.14
    pects
    0.13
    cribing
    0.12
    dann
    0.12
    sembles
    0.12
    cribes
    0.11
     follows
    0.11
    /from
    0.11
    Activations Density 0.414%

    No Known Activations