© 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. 45430
    Prev
    Next
    INDEX
    Explanations

    max int

    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
    azz
    -0.08
    ä¸Ģæ»´
    -0.08
    IGH
    -0.08
    ×¢×ķת
    -0.08
    rades
    -0.08
    æ¸Ī
    -0.08
    åħ¬åı¸ä¸ļåĬ¡
    -0.07
    idak
    -0.07
      ↵    ↵
    -0.07
    urras
    -0.07
    POSITIVE LOGITS
    te
    0.07
    0.07
     bri
    0.07
    ä¿Ĭ
    0.06
    ings
    0.06
    sc
    0.06
    ä¿¡æīĺ
    0.06
    ite
    0.06
    reg
    0.06
    ivr
    0.06
    Activations Density 0.202%

    No Known Activations