© 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. 62113
    Prev
    Next
    INDEX
    Explanations

    URL path segments

    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
    ä¸įä»İ
    -0.08
    å¤ļå¾Ĺ
    -0.07
    izedName
    -0.07
    è¡
    -0.07
    æĪijåı«
    -0.07
     Sole
    -0.07
    ather
    -0.07
    è´·
    -0.07
    leh
    -0.07
    aghan
    -0.07
    POSITIVE LOGITS
     preceded
    0.08
     beserta
    0.08
     lisäksi
    0.07
    éĻĦ带
    0.07
     illustr
    0.07
    以åıĬä¸ĢäºĽ
    0.07
    åIJĮæŶè¿ĺ
    0.06
     seed
    0.06
    UI
    0.06
    以åıĬ缸åħ³
    0.06
    Activations Density 0.005%

    No Known Activations