© 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. 47544
    Prev
    Next
    INDEX
    Explanations

    version numbers

    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
    ¹Ħ
    -0.08
    ovsky
    -0.08
     sqr
    -0.08
    /cgi
    -0.08
    /=
    -0.08
    æ¯įçļĦ
    -0.07
    åįģæĹ¥
    -0.07
    otts
    -0.07
    RACT
    -0.07
     Stephens
    -0.07
    POSITIVE LOGITS
    alth
    0.08
    ycl
    0.07
    afe
    0.07
    bund
    0.07
    丽åįİ
    0.06
    ingen
    0.06
    鼶鼶
    0.06
    ntax
    0.06
    ee
    0.06
     à¹Ĩ
    0.06
    Activations Density 0.113%

    No Known Activations