© 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. 1269
    Prev
    Next
    INDEX
    Explanations

    optical wiring member

    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
     zr
    -0.06
    è¯¥ä½ľèĢħ
    -0.06
    esel
    -0.06
    è¯Ľä»Ļ
    -0.06
    urm
    -0.06
    çŁ³åĻ¨
    -0.06
    æĺł
    -0.06
    æĤŁç©º
    -0.06
    =size
    -0.06
    enberg
    -0.06
    POSITIVE LOGITS
    auen
    0.09
    unte
    0.08
    elter
    0.08
    人åķĬ
    0.08
    éĢļè¿ĩ以ä¸Ĭ
    0.07
    ÅĽle
    0.07
    ached
    0.07
    è¶Ĭèµ°
    0.07
    ỹ
    0.07
    elix
    0.07
    Activations Density 0.011%

    No Known Activations