© 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. 43364
    Prev
    Next
    INDEX
    Explanations

    children and daughters

    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
    èıľè°±
    -0.08
    æĿ¥åĩ½
    -0.07
    zcze
    -0.07
    rypton
    -0.07
    çŃĿ
    -0.07
    erb
    -0.07
    Weekly
    -0.06
     tslint
    -0.06
    çł
    -0.06
    ä¼¼
    -0.06
    POSITIVE LOGITS
    å¾Ģ常ä¸Ģæł·
    0.09
     accompanied
    0.08
     ÑģопÑĢовожда
    0.08
     accompagnato
    0.08
    éĻªåIJĮä¸ĭ
    0.08
     accompagné
    0.08
     alasti
    0.08
     doprovod
    0.08
    åħ´å¥ĭçļĦ
    0.07
    uzzi
    0.07
    Activations Density 0.358%

    No Known Activations