© 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. 43989
    Prev
    Next
    INDEX
    Explanations

    discourse completion

    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
     seped
    -0.08
    )","
    -0.08
    );}
    -0.08
    ?>/
    -0.08
    ?”,
    -0.08
    æĪĸæľª
    -0.08
    ï¼ģ**
    -0.08
    ();"
    -0.08
     thereof
    -0.08
    **”,
    -0.08
    POSITIVE LOGITS
    :
    0.07
     regarding
    0.07
     terj
    0.07
    ':
    0.07
    nam
    0.06
    åĽłä¸ºåľ¨
    0.06
    å·®å¼Ĥ
    0.06
    ìĬµ
    0.06
    tere
    0.06
    ìĹĪëĬĶëį°
    0.06
    Activations Density 1.167%

    No Known Activations