© 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. 8209
    Prev
    Next
    INDEX
    Explanations

    single cell Range

    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
    kaw
    -0.08
    rü
    -0.07
    éĢĨ
    -0.07
    ossi
    -0.07
    kowski
    -0.07
    auen
    -0.07
    kish
    -0.07
    bergen
    -0.07
     kolej
    -0.07
    åħ¨éĿ¢å®ĮæĪIJ
    -0.07
    POSITIVE LOGITS
     single
    0.17
    .single
    0.16
     Single
    0.16
    /single
    0.16
    Single
    0.16
    single
    0.15
    åįķä¸Ģ
    0.15
    åįķ
    0.15
    åıªæľīä¸Ģ个
    0.15
     SINGLE
    0.15
    Activations Density 0.167%

    No Known Activations