© 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. 56604
    Prev
    Next
    INDEX
    Explanations

    perspective

    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
    æ®Ĩå°½
    -0.10
    à¸Ķà¹Į
    -0.10
    zelfde
    -0.09
     scolaires
    -0.09
    RARY
    -0.08
    hardt
    -0.08
    zinho
    -0.08
    arger
    -0.08
    urg
    -0.08
    urga
    -0.08
    POSITIVE LOGITS
    pective
    0.09
    oins
    0.08
    ences
    0.08
    isit
    0.08
    pectives
    0.08
    ally
    0.08
    acular
    0.07
    åĬŀåħ¬åİħ
    0.07
    ê¹Ķ
    0.07
    zysta
    0.07
    Activations Density 0.029%

    No Known Activations