© 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. 13678
    Prev
    Next
    INDEX
    Explanations

    .END//

    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
    ,'\
    -0.07
    æľ¬ç¤¾
    -0.07
    erson
    -0.07
    udios
    -0.07
     Acc
    -0.06
    ä¸įéĢı
    -0.06
    acc
    -0.06
    qual
    -0.06
    aciones
    -0.06
    keit
    -0.06
    POSITIVE LOGITS
    oley
    0.08
    ä¸įå¾Ĺä»İäºĭ
    0.08
    #endregion
    0.07
    edor
    0.07
    illet
    0.07
    ggi
    0.07
    eneur
    0.07
    åĭĺ
    0.07
    rody
    0.07
    ekh
    0.07
    Activations Density 0.233%

    No Known Activations