© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 50146
    Prev
    Next
    INDEX
    Explanations

    code elements like $ and :

    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
    lette
    -0.08
    akil
    -0.08
    odont
    -0.08
    engk
    -0.08
    ubi
    -0.08
    allen
    -0.08
    è·¯å°ıåѦ
    -0.08
    sterol
    -0.08
    Yaw
    -0.08
    _CHAT
    -0.08
    POSITIVE LOGITS
    è¨Ģéģĵ
    0.06
    -
    0.06
    Ń
    0.06
    ?
    0.06
    R
    0.06
     R
    0.06
    (
    0.05
    0.05
    å¤ļåĬ¨
    0.05
     D
    0.05
    Activations Density 0.373%

    No Known Activations