© 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. 45240
    Prev
    Next
    INDEX
    Explanations

    cover collaborator, salary, IP Fake, payment, London England, invisible button

    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
    aight
    -0.07
     ($.
    -0.07
    zilla
    -0.07
    ffel
    -0.06
    igli
    -0.06
     (`
    -0.06
    身åIJİçļĦ
    -0.06
    è¿Ļæĺ¯ä¸Ģ款
    -0.06
    ilde
    -0.06
    çķĻç»Ļ
    -0.06
    POSITIVE LOGITS
     )
    0.07
    Ñģнабжение
    0.07
     Harapan
    0.07
    êµī
    0.07
    ackson
    0.07
    евÑģкого
    0.06
    ).
    0.06
     ejemp
    0.06
    ·
    0.06
    麦åħĭ
    0.06
    Activations Density 0.884%

    No Known Activations