© 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. 11591
    Prev
    Next
    INDEX
    Explanations

    correctly returns value

    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
    pei
    -0.08
    寡å¦ĩ
    -0.08
    mena
    -0.08
    pose
    -0.07
    afi
    -0.07
     UserID
    -0.07
    ãn
    -0.07
    annels
    -0.07
    _dropout
    -0.07
    anyi
    -0.07
    POSITIVE LOGITS
     correctly
    0.10
     accurately
    0.09
     accurate
    0.09
    æŃ£ç¡®
    0.09
     correct
    0.08
    符åIJĪ
    0.08
     appropriately
    0.07
    æŃ£ç¡®åľ°
    0.07
     Correct
    0.07
    ä¸įæĩĪ
    0.07
    Activations Density 0.003%

    No Known Activations