© 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. 27228
    Prev
    Next
    INDEX
    Explanations

    subject to

    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
    ¾
    -0.10
    throp
    -0.08
    encontre
    -0.08
    Ïģθ
    -0.08
    तर
    -0.08
    vironment
    -0.08
    ç¼¥
    -0.08
    注åĨĮæŶéĹ´
    -0.08
    िश
    -0.08
    rosse
    -0.08
    POSITIVE LOGITS
    ly
    0.12
    ively
    0.12
    ivity
    0.10
    eur
    0.09
    eer
    0.08
    ious
    0.08
    ivities
    0.08
    ably
    0.07
    hood
    0.07
    auf
    0.07
    Activations Density 0.064%

    No Known Activations