© 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. 60949
    Prev
    Next
    INDEX
    Explanations

    image file names and figures

    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
    agin
    -0.08
    èĥ¤
    -0.07
    urry
    -0.07
    å´İ
    -0.07
    è¿İæĸ°
    -0.07
    ŀ
    -0.06
    Ups
    -0.06
    央è§Ĩç½ij
    -0.06
    è¿ŀäºij
    -0.06
    ä¸ĵæłıæĶ¶å½ķ该åĨħ容
    -0.06
    POSITIVE LOGITS
    åĽ¾
    0.11
    åĽ¾ä¸º
    0.09
    .png
    0.09
    Figure
    0.08
     ![
    0.08
    .jpeg
    0.08
    ![
    0.08
    igure
    0.08
     Photo
    0.08
     Figura
    0.08
    Activations Density 0.718%

    No Known Activations