© 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. 43739
    Prev
    Next
    INDEX
    Explanations

    GPS, surgical, gallery, feeding, center, neuro

    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
    outh
    -0.07
    建çŃijè£ħ饰
    -0.06
     Grote
    -0.06
    usty
    -0.06
    ÑĢез
    -0.06
    羣
    -0.06
    jons
    -0.06
    çĦ
    -0.06
     doubtful
    -0.06
    ldre
    -0.06
    POSITIVE LOGITS
     Atra
    0.07
    rza
    0.07
    eku
    0.07
    eltas
    0.07
    rat
    0.07
    Êľ
    0.07
    baru
    0.07
    biet
    0.07
    çļĦå°ıç¼ĸ
    0.06
    nitz
    0.06
    Activations Density 0.897%

    No Known Activations