© 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. 10022
    Prev
    Next
    INDEX
    Explanations

    phrases starting with "where"

    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
    ož
    -0.09
    oÄį
    -0.09
     volna
    -0.08
    erber
    -0.08
    -0.08
    èĢĮè¦ģ
    -0.08
    swith
    -0.08
    ัà¸ĩ
    -0.08
    æľīæīĢæĢĿ
    -0.08
    ä¹ĭéĹ´çļĦæĦŁæĥħ
    -0.08
    POSITIVE LOGITS
    upon
    0.16
    abouts
    0.15
    quiera
    0.13
    soever
    0.10
    -ever
    0.10
    /if
    0.10
    ering
    0.09
    ered
    0.09
     Ñĥгодно
    0.09
    kolwiek
    0.09
    Activations Density 0.075%

    No Known Activations