© 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. 45858
    Prev
    Next
    INDEX
    Explanations

    roof and ceiling structures

    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
     uphill
    -0.08
    nett
    -0.07
    ä»ĭ
    -0.07
    ãĤ´ãĥ¼ãĥ«ãĥī
    -0.07
    /OR
    -0.07
    angun
    -0.07
    ç¥ł
    -0.07
    laufen
    -0.06
     acu
    -0.06
    èĤ¿èĥĢ
    -0.06
    POSITIVE LOGITS
     overhead
    0.13
    天èĬ±
    0.12
    å±ĭ顶
    0.11
    头顶
    0.11
     canopy
    0.10
    天çªĹ
    0.10
     roof
    0.10
    顶
    0.10
    åIJĬ顶
    0.10
    ä¸ĭæĿ¥çļĦ
    0.10
    Activations Density 0.071%

    No Known Activations