© 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. 2560
    Prev
    Next
    INDEX
    Explanations

    assignments and definitions

    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
    ียà¸Ķ
    -0.08
    chino
    -0.07
    bd
    -0.07
    ingat
    -0.07
    bs
    -0.07
    chia
    -0.07
    ending
    -0.06
    ild
    -0.06
    ching
    -0.06
    uye
    -0.06
    POSITIVE LOGITS
     accordingly
    0.08
    ãģ¯ãģĿãģ®
    0.08
    венÑĤа
    0.07
    onor
    0.07
     dessus
    0.07
    AGER
    0.07
    è¿ĻäºĽå°ı
    0.07
    ostar
    0.07
    对è¿ĻäºĽ
    0.07
    æīĢæľīè¿ĻäºĽ
    0.07
    Activations Density 0.022%

    No Known Activations