© 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. 22793
    Prev
    Next
    INDEX
    Explanations

    placenames parts

    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
    Å¡ek
    -0.08
    acci
    -0.07
    åľ¨ä¸Ģå®ļ
    -0.07
     Nürn
    -0.07
    çĻ»è®°è¡¨
    -0.07
    çķªç¦º
    -0.07
    americano
    -0.07
     Cear
    -0.07
     Palacio
    -0.07
    éĽħåħ¸
    -0.07
    POSITIVE LOGITS
    ecas
    0.08
    éĺģä¸ĭ
    0.07
    megen
    0.07
    缴è¾ĸ
    0.07
    uling
    0.07
    czo
    0.07
    åĴĢ
    0.07
     بض
    0.07
    embourg
    0.07
    äº¬ä¸ľ
    0.07
    Activations Density 0.563%

    No Known Activations