© 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. 3279
    Prev
    Next
    INDEX
    Explanations

    code delimiters and special characters

    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
    enet
    -0.07
    éĻĮ
    -0.07
    aille
    -0.07
    å°ıåĪĨéĺŁ
    -0.07
    å©·
    -0.07
    éĻĽ
    -0.07
    chy
    -0.07
    acol
    -0.07
     tact
    -0.07
    纶
    -0.07
    POSITIVE LOGITS
    象
    0.08
    ierge
    0.07
    uger
    0.07
    è´
    0.07
    aland
    0.06
    %=
    0.06
    ãģ§ãģĻãĤĪ
    0.06
    .embed
    0.06
    +-+-
    0.06
    /***/
    0.06
    Activations Density 0.002%

    No Known Activations