© 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. 43756
    Prev
    Next
    INDEX
    Explanations

    cities, organizations, contrasting states

    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
    ä¸įèIJ½
    -0.08
    èĢĮéĿŀ
    -0.08
    èĢĮä¸įæĺ¯
    -0.08
     whereas
    -0.07
    åħĭåħ°
    -0.07
    ä¸įåĥı
    -0.07
    åIJįåī¯
    -0.07
     rather
    -0.07
    ä¸įåIJĮäºİ
    -0.07
    unan
    -0.07
    POSITIVE LOGITS
    åIJİèĢħ
    0.13
    åīįèĢħ
    0.11
     latter
    0.09
    etton
    0.09
    两èĢħ
    0.09
    ugi
    0.09
    åĨįåĪ°
    0.08
     gleicher
    0.08
    äºĮèĢħ
    0.08
    åĽĬ
    0.07
    Activations Density 0.204%

    No Known Activations