© 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. 46829
    Prev
    Next
    INDEX
    Explanations

    end of sentence, new paragraph

    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
    UNDLE
    -0.08
    antly
    -0.08
    oped
    -0.07
    odia
    -0.07
     ageing
    -0.07
    à¸ģัà¸Ļà¹Ģลย
    -0.07
    lients
    -0.07
    ä¸ĢæľŁå·¥ç¨ĭ
    -0.07
    å¤ĸéĥ¨çݯå¢ĥ
    -0.07
    äºĨæĮĩ
    -0.07
    POSITIVE LOGITS
    oria
    0.07
    DOMNode
    0.07
    acin
    0.07
     Dig
    0.07
    dig
    0.06
    idar
    0.06
    Dig
    0.06
    åĵģéī´
    0.06
    ouch
    0.06
    óa
    0.06
    Activations Density 0.001%

    No Known Activations