© 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. 28179
    Prev
    Next
    INDEX
    Explanations

    artery or generate

    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
     beide
    -0.07
    room
    -0.07
    ç³Ł
    -0.07
     оба
    -0.07
    .socket
    -0.07
     ambas
    -0.06
    è¿Ļ两ç§į
    -0.06
     обоиÑħ
    -0.06
    çĭ¬
    -0.06
     ambos
    -0.06
    POSITIVE LOGITS
    oreach
    0.07
     collectively
    0.07
    ÙĪز
    0.07
    亢
    0.07
    (each
    0.07
     summ
    0.07
    ramid
    0.07
    ë³Ħë¡ľ
    0.07
    naio
    0.07
     tÆ°á»Łng
    0.07
    Activations Density 0.093%

    No Known Activations