© 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. 14870
    Prev
    Next
    INDEX
    Explanations

    MO, RO, vo, iro, EGO, æo

    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
    ÑĤÑĢ
    -0.13
    ãĥ£ãĥ³
    -0.12
    à¸Ļà¹īà¸Ńย
    -0.11
    rÅijl
    -0.10
    ually
    -0.10
    most
    -0.10
    nos
    -0.10
    à¸Ļà¹īำ
    -0.09
    lah
    -0.09
    د
    -0.09
    POSITIVE LOGITS
     ìĿ¸íķľ
    0.15
     ìĿ¸íķ´
    0.15
    gether
    0.12
    cean
    0.12
    xygen
    0.12
    vertime
    0.12
    à¦ģ
    0.12
    åĵĩ
    0.11
    ptions
    0.11
    ffset
    0.11
    Activations Density 2.401%

    No Known Activations