© 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. 57035
    Prev
    Next
    INDEX
    Explanations

    etc

    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
    irl
    -0.07
    çĤ¹æѤ
    -0.07
    å¸Ĥå§Ķç»Ħç»ĩéĥ¨
    -0.07
    ãĢħ
    -0.07
    idro
    -0.06
    idt
    -0.06
    uern
    -0.06
    ?,?,?,?,
    -0.06
    _Native
    -0.06
    agara
    -0.06
    POSITIVE LOGITS
     etc
    0.18
    etc
    0.14
    ãģĿãģĹãģ¦
    0.12
    çŃīçŃī
    0.12
    管çIJĨçŃī
    0.12
     ÙĪغÙĬرÙĩا
    0.11
     ê·¸ë¦¬ê³ł
    0.11
     ฯลฯ
    0.11
    æ³ķçŃī
    0.11
    ãģªãģ©ãģĮ
    0.11
    Activations Density 0.207%

    No Known Activations