© 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. 38013
    Prev
    Next
    INDEX
    Explanations

    people's names or titles

    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
    ehme
    -0.09
    åľ¨æľ¬ç«Ļ
    -0.09
    adır
    -0.08
    iliz
    -0.08
    ç¦ģä¸įä½ı
    -0.08
    IRQ
    -0.08
    åħīå±±
    -0.08
    äºĨ解ä¸ĭ
    -0.08
    aviest
    -0.08
    ebro
    -0.08
    POSITIVE LOGITS
    Âł
    0.11
     blah
    0.10
     fucking
    0.08
     sogenannte
    0.07
     supposedly
    0.07
    âĢ¦
    0.07
     fucked
    0.07
    -
    0.07
    ä¸Ģåħ±æľī
    0.07
    ÂŃ
    0.06
    Activations Density 0.333%

    No Known Activations