© 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. 19417
    Prev
    Next
    INDEX
    Explanations

    plane, lateral, horizontal, radial, axes

    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
     caden
    -0.08
    mon
    -0.08
    olgen
    -0.07
    meld
    -0.07
     puntu
    -0.07
    çľŁä¼ª
    -0.07
    å¼ıçļĦ
    -0.07
    ë¡ł
    -0.07
     Mon
    -0.07
    tam
    -0.07
    POSITIVE LOGITS
    plane
    0.08
     plane
    0.08
    -plane
    0.08
    å¹³éĿ¢
    0.07
     Plane
    0.07
    _plane
    0.07
    Plane
    0.07
    å±ķè§Īå±ķ示
    0.07
     lateral
    0.07
     directions
    0.07
    Activations Density 0.007%

    No Known Activations