© 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. 47521
    Prev
    Next
    INDEX
    Explanations

    mathematical function properties

    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
     false
    -0.07
    plex
    -0.06
    åĨ³å®ļ
    -0.06
    plural
    -0.06
     adjacent
    -0.06
    缸éĤ»
    -0.06
    istance
    -0.06
    itest
    -0.06
     override
    -0.06
    æĸ¯åĿ¦
    -0.06
    POSITIVE LOGITS
    ELD
    0.09
    ÑĢоди
    0.09
    TXT
    0.09
    udan
    0.08
    rapped
    0.08
    Haus
    0.08
    uvre
    0.08
    elf
    0.08
     részlet
    0.08
    Fel
    0.08
    Activations Density 0.005%

    No Known Activations