© 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. 65363
    Prev
    Next
    INDEX
    Explanations

    list initialization

    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
    .props
    -0.09
    uspend
    -0.08
    åģļ人çļĦ
    -0.08
    åħħå®ŀèĩªå·±
    -0.07
    .heroku
    -0.07
    вик
    -0.07
    chemas
    -0.07
    ienne
    -0.07
    èĤĨ
    -0.07
     merce
    -0.07
    POSITIVE LOGITS
    磨
    0.06
     Ele
    0.06
    aud
    0.06
    akis
    0.06
     necessary
    0.06
     Scr
    0.06
    Vit
    0.06
     Vit
    0.06
    Aud
    0.06
    IRO
    0.06
    Activations Density 0.014%

    No Known Activations