© 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. 8790
    Prev
    Next
    INDEX
    Explanations

    mathematical notation code blocks

    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·¯éĢı
    -0.10
    DIR
    -0.09
    å·¥ç¨ĭçŃī
    -0.09
    å¾ħç»Ń
    -0.09
     COMPR
    -0.08
    {name
    -0.08
    æĬ¥åIJįæŶ
    -0.08
     *))
    -0.08
    =>'
    -0.08
    ius
    -0.08
    POSITIVE LOGITS
    åħ¶ä¸Ń
    0.07
    以åıĬ
    0.07
    ↵
    0.07
    ä¹Łå°±æĺ¯è¯´
    0.06
     âĢ¦.
    0.06
    âĢ¦.
    0.06
     âĢ¦
    0.06
     oppure
    0.06
    ï¼Ī
    0.06
     sekä
    0.06
    Activations Density 0.018%

    No Known Activations