© 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. 33514
    Prev
    Next
    INDEX
    Explanations

    money or revenue

    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
    ropp
    -0.08
    WithData
    -0.07
    hait
    -0.07
    inkan
    -0.07
    åħĭåħ°
    -0.07
    ebol
    -0.07
    cky
    -0.07
    èĬĤå¿«ä¹IJ
    -0.07
    izard
    -0.07
    ÑģÑĤвÑĥ
    -0.06
    POSITIVE LOGITS
    丰åİļçļĦ
    0.08
    丰åİļ
    0.08
    åĪĨéħįçļĦ
    0.07
    æķ°é¢Ŀ
    0.07
    åĴĮç²¾ç¥ŀ
    0.07
    æµģåIJij
    0.07
    åĪĨéħį
    0.07
    ahari
    0.07
    ray
    0.07
    丰
    0.07
    Activations Density 0.363%

    No Known Activations