© 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. 28690
    Prev
    Next
    INDEX
    Explanations

    cant

    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
    heimer
    -0.07
     anun
    -0.07
    azzo
    -0.07
    dash
    -0.07
    Reserved
    -0.07
    https
    -0.06
    azza
    -0.06
    èĢģ人家
    -0.06
    念
    -0.06
    zol
    -0.06
    POSITIVE LOGITS
    HCI
    0.08
     fabr
    0.08
     FIS
    0.07
    дове
    0.07
    ooks
    0.07
    áĥķáĥĶ
    0.07
    dob
    0.07
    dir
    0.07
    عÙĪ
    0.07
    agai
    0.07
    Activations Density 0.045%

    No Known Activations