© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 61671
    Prev
    Next
    INDEX
    Explanations

    time, position, department, hiring manager

    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
    ecker
    -0.07
    èĥĨ
    -0.06
    gew
    -0.06
     Kies
    -0.06
    æĪĴ
    -0.06
     зако
    -0.06
    vin
    -0.06
    yczy
    -0.06
    ÙģاÙĤ
    -0.06
    ostal
    -0.06
    POSITIVE LOGITS
    inus
    0.07
    ãģ®ç¢ºèªį
    0.07
    pard
    0.07
    ovil
    0.07
    èIJ¥ä¸ļéĥ¨
    0.07
     MUNICIP
    0.07
     volna
    0.07
    Snapshot
    0.07
     =========================================================================
    0.07
    atriz
    0.07
    Activations Density 0.101%

    No Known Activations