© 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. 25311
    Prev
    Next
    INDEX
    Explanations

    internal entities and functions

    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
     outdoors
    -0.07
    xffffffff
    -0.07
    esten
    -0.07
    éľĸ
    -0.07
    epar
    -0.07
    неÑģиÑĤе
    -0.07
    неÑģен
    -0.07
     latter
    -0.07
    enni
    -0.07
    frey
    -0.07
    POSITIVE LOGITS
    åĴĮå¤ĸ
    0.17
    (internal
    0.14
    /internal
    0.13
    /out
    0.13
     workings
    0.12
    /Internal
    0.12
    æ·±å¤ĦçļĦ
    0.11
    (inner
    0.10
    most
    0.10
    çĶŁäº§æĢ»åĢ¼
    0.10
    Activations Density 0.205%

    No Known Activations