© 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. 4007
    Prev
    Next
    INDEX
    Explanations

    K or .com

    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
    iba
    -0.07
    ноп
    -0.06
     Pant
    -0.06
    æĥħåĨµè¯´æĺİ
    -0.06
    åĨµ
    -0.06
    äºĭäºĭ
    -0.06
    客æ°Ķ
    -0.06
    èĩ´
    -0.06
    足çļĦ
    -0.06
    åĨħ容çļĦ羣å®ŀæĢ§
    -0.06
    POSITIVE LOGITS
    åĴĮçĻ½
    0.08
    edata
    0.07
    ornings
    0.07
    дÑĢÑĭ
    0.07
    anei
    0.07
    åıĬéħįå¥Ĺ
    0.07
    дÑĢÑĥ
    0.07
    oniques
    0.07
    ä¾ĽåºĶ产åĵģ
    0.07
    aminer
    0.07
    Activations Density 0.001%

    No Known Activations