© 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. 9390
    Prev
    Next
    INDEX
    Explanations

    url, "Failed" status

    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
    管
    -0.07
    å¿ĥä¸Ń
    -0.07
    agn
    -0.06
    æ±ł
    -0.06
    å°±ç®Ĺ
    -0.06
    สมัà¸Ħร
    -0.06
    è¿ŀ带
    -0.06
    éĩijéĻµ
    -0.06
     reminis
    -0.06
    éĹ¹
    -0.06
    POSITIVE LOGITS
    éģĹçĹĩ
    0.08
    详尽
    0.07
    -divider
    0.07
    åĦ¿ç«¥åĮ»éĻ¢
    0.07
    ä¸įçģŃ
    0.07
    详
    0.07
    äºĨä»Ģä¹Ī
    0.07
    çģ«äºĨ
    0.07
    ãĥĨãĥ¼
    0.07
    venues
    0.07
    Activations Density 0.005%

    No Known Activations