© 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. 43092
    Prev
    Next
    INDEX
    Explanations

    title:

    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
    ewise
    -0.07
    彬
    -0.07
    ÙĪع
    -0.07
    ä¸Ģ鸣
    -0.07
    agan
    -0.07
    /about
    -0.07
    owl
    -0.06
    aisen
    -0.06
    ylon
    -0.06
    ä»İè¿Ļ个
    -0.06
    POSITIVE LOGITS
    ores
    0.09
    rite
    0.08
    azionale
    0.07
    รม
    0.07
    ศัà¸ģà¸Ķิà¹Į
    0.07
    اÙĤ
    0.07
    ¾
    0.07
    åIJĮä¸Ĭ
    0.07
    åħ³èĬĤ
    0.06
    RITE
    0.06
    Activations Density 0.043%

    No Known Activations