© 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
    2. Qwen3.5-9B Base
    3. 15-QWENSCOPE-RES-64K
    4. 19176
    Prev
    Next
    INDEX
    Explanations

    text surrounding punctuation

    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
    cox
    -0.07
    ç´¢
    -0.07
    Ø´Ùħ
    -0.06
    aka
    -0.06
     brushed
    -0.06
    one
    -0.06
    èŀį
    -0.06
    代表æĢ§
    -0.06
    enson
    -0.06
    对éĶĻ
    -0.06
    POSITIVE LOGITS
    ...</
    0.10
    ...**
    0.10
    :...
    0.09
    ...]
    0.09
    ...",
    0.09
    ...*
    0.09
    ...\
    0.09
    ...(
    0.08
     ..."
    0.08
     ...\
    0.08
    Activations Density 0.094%

    No Known Activations