© 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. 12398
    Prev
    Next
    INDEX
    Explanations

    frontline, roots, field, peripheral

    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
    avantage
    -0.08
    ielding
    -0.08
    .framework
    -0.08
    ượt
    -0.08
    åīĸèħ¹
    -0.08
    -caret
    -0.08
    íĭĢ
    -0.08
    çĻĸ
    -0.07
    èµ°éģį
    -0.07
     Convention
    -0.07
    POSITIVE LOGITS
    第ä¸Ģ线
    0.11
    /front
    0.08
    -most
    0.08
    ers
    0.08
    /local
    0.08
    çĶ¸
    0.08
    ä¸Ģ线çļĦ
    0.07
    å®ŀéĻħåĩºåıij
    0.07
    è¿Ļæł·æĤ¨å°±åı¯ä»¥
    0.07
    åĬŀäºĭ
    0.07
    Activations Density 0.051%

    No Known Activations