© 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. 18933
    Prev
    Next
    INDEX
    Explanations

    acquisition year or version details

    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
    nade
    -0.08
    heder
    -0.08
    åIJįåī¯
    -0.08
    kip
    -0.08
    /manage
    -0.08
    ä¸ĩ亿
    -0.08
    imers
    -0.07
    rure
    -0.07
    ubre
    -0.07
    _]
    -0.07
    POSITIVE LOGITS
    å¤ĩ注
    0.08
     details
    0.07
     reason
    0.07
    翼
    0.07
    éĻĨ
    0.06
    reason
    0.06
    ikken
    0.06
    åİŁåĽł
    0.06
     bathrooms
    0.06
    elper
    0.06
    Activations Density 0.055%

    No Known Activations