© 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. 43180
    Prev
    Next
    INDEX
    Explanations

    counterclockwise, clockwise, countercurrent

    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
    éĿŀåħ¬
    -0.08
    ink
    -0.08
    ä¸įæĬĺä¸įæī£
    -0.08
    asl
    -0.08
    either
    -0.08
    accio
    -0.07
    inhas
    -0.07
    ä¸įæĦģ
    -0.07
    anity
    -0.07
    lay
    -0.07
    POSITIVE LOGITS
    wards
    0.07
    ziej
    0.07
    /right
    0.07
    /up
    0.07
    worthy
    0.07
    zaam
    0.07
    stunden
    0.07
    rist
    0.07
    ward
    0.07
    umann
    0.06
    Activations Density 0.001%

    No Known Activations