© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 23270
    Prev
    Next
    INDEX
    Explanations

    `_rot` or `rotated`

    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
    stin
    -0.08
    mart
    -0.08
    æĿ¥äºº
    -0.07
    ohan
    -0.07
    anam
    -0.07
    /videos
    -0.07
    rosa
    -0.07
    ATER
    -0.07
    urat
    -0.07
    çī¹æĸ¯
    -0.07
    POSITIVE LOGITS
    irth
    0.08
    uban
    0.07
    ä¸ĩåı¤
    0.07
    CENT
    0.07
    çİīå±±
    0.07
    (turn
    0.07
    izen
    0.07
    OVE
    0.07
    æĹ¥åIJij
    0.07
    rlen
    0.06
    Activations Density 0.115%

    No Known Activations