© 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. 42867
    Prev
    Next
    INDEX
    Explanations

    Forsyth or independent Nursery

    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
    acu
    -0.07
    è¿ĩåİ»äºĨ
    -0.07
    ihan
    -0.07
    _dispatcher
    -0.07
    çģ¯çļĦ
    -0.07
    å°Ķ夫
    -0.07
    jh
    -0.07
    aghan
    -0.06
    .fn
    -0.06
    è¡Ĺåı£
    -0.06
    POSITIVE LOGITS
    SIZE
    0.07
    untung
    0.07
    .documentation
    0.07
    γÎŃν
    0.07
    oción
    0.07
    imension
    0.07
    Ø
    0.06
    illus
    0.06
    reeNode
    0.06
    帽
    0.06
    Activations Density 0.006%

    No Known Activations