© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 64030
    Prev
    Next
    INDEX
    Explanations

    title or name

    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
    ëĤ´
    -0.07
    èı²çī¹
    -0.07
    zon
    -0.07
    åĩºè´¨
    -0.07
    ç¥ł
    -0.07
    marsh
    -0.07
    éĩıçļĦ
    -0.07
    éĩı为
    -0.07
    åħĭç¦ı
    -0.07
    è´¢åĬ¡äººåijĺ
    -0.06
    POSITIVE LOGITS
    åIJį称
    0.12
    /title
    0.12
     name
    0.12
    è¿Ļ个åIJįåŃĹ
    0.11
    -name
    0.11
    åIJį稱
    0.11
     title
    0.11
     titles
    0.11
    name
    0.11
     names
    0.11
    Activations Density 0.256%

    No Known Activations