© 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. 42686
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    JAKARTA
    -0.08
    ishes
    -0.07
    åłĤ
    -0.07
    iger
    -0.07
    late
    -0.07
    halts
    -0.07
    éħĮ
    -0.07
    åĸ·å°Ħ
    -0.07
    è¿Ļæł·æĤ¨å°±åı¯ä»¥
    -0.07
    å®ħéħį
    -0.07
    POSITIVE LOGITS
    .listen
    0.06
    继ç»Ńä¿ĿæĮģ
    0.06
    Min
    0.06
     sh
    0.06
    对ä¼ģä¸ļ
    0.06
    _strlen
    0.06
     Aver
    0.06
    aly
    0.06
    ãģªãģĦãĤĪãģĨãģ«
    0.06
    erk
    0.06
    Activations Density 0.000%

    No Known Activations