© 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. 9908
    Prev
    Next
    INDEX
    Explanations

    code constructors or variables

    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
    ifo
    -0.07
    är
    -0.06
    éħ¿
    -0.06
     din
    -0.06
    ak
    -0.06
    ÙĦا
    -0.06
     Bernd
    -0.05
    :o
    -0.05
    -m
    -0.05
    æĺ¯å¤©
    -0.05
    POSITIVE LOGITS
    materi
    0.08
    icch
    0.08
    á»ķi
    0.08
    ä¹IJ天
    0.08
    çİĩè¾¾åĪ°
    0.08
    ãĤ±ãĥ¼ãĥĪ
    0.08
    sev
    0.08
     intervent
    0.07
    åIJĪåIJĮæŶ
    0.07
    apte
    0.07
    Activations Density 0.019%

    No Known Activations