© 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. 16891
    Prev
    Next
    INDEX
    Explanations

    known to be

    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
    obie
    -0.08
     info
    -0.08
    åı¦æľī
    -0.08
     maybe
    -0.07
     %.
    -0.07
    hoven
    -0.07
     magari
    -0.07
    ffy
    -0.07
     appunto
    -0.07
    åıĪæľī
    -0.07
    POSITIVE LOGITS
     infatti
    0.09
     firstly
    0.07
    ogl
    0.07
     fascin
    0.07
    ``,
    0.07
     λοι
    0.07
     ugyanis
    0.07
    å²ģçļĦæŶåĢĻ
    0.07
     zatem
    0.06
    ",[
    0.06
    Activations Density 0.147%

    No Known Activations