© 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. 23602
    Prev
    Next
    INDEX
    Explanations

    k followed by certain words

    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
    ä¸Ģä¸ĸ
    -0.09
    ä¸Ģåı¶
    -0.07
    åıijå±ķçļĦ
    -0.07
    EventArgs
    -0.07
    ellement
    -0.07
    lach
    -0.07
    çŃĭ骨
    -0.07
    管çIJĨç±»
    -0.07
    ä»ħä»£è¡¨ä½ľèĢħ
    -0.07
    ä¸Ģè¾Ī
    -0.07
    POSITIVE LOGITS
    hr
    0.07
     Noi
    0.06
    از
    0.06
    ilter
    0.06
    èĽ
    0.06
    iros
    0.06
    èį·
    0.06
    iator
    0.06
    rant
    0.06
     circol
    0.06
    Activations Density 0.010%

    No Known Activations