© 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. 62334
    Prev
    Next
    INDEX
    Explanations

    appeal, character, charm

    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
    è¿Ļæł·æĤ¨å°±åı¯ä»¥
    -0.08
    ÑĤо
    -0.08
    ement
    -0.08
    ements
    -0.08
    heits
    -0.08
    sWith
    -0.08
    UIL
    -0.08
     araya
    -0.08
    å±ħæĺĵ
    -0.07
    обÑĢа
    -0.07
    POSITIVE LOGITS
    åįģ足çļĦ
    0.15
    åįģ足
    0.14
    åı¯è¨Ģ
    0.13
    åĽĽå°Ħ
    0.11
    ìŀĪëĬĶ
    0.09
    lessness
    0.09
    ously
    0.09
    ä½ķåľ¨
    0.09
    ãģ®ãģĤãĤĭ
    0.09
     ìŀĪëĬĶ
    0.08
    Activations Density 0.036%

    No Known Activations