© 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. 4097
    Prev
    Next
    INDEX
    Explanations

    numbers less than a value

    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
    ä¸įè§ģäºĨ
    -0.09
    åıĪåIJį
    -0.07
    åIJİèĩ³
    -0.07
    åıĪ称
    -0.07
     *__
    -0.07
    opping
    -0.07
    ä¸į欲
    -0.07
     appunto
    -0.07
    Ùĥات
    -0.06
    éķ¿çº¦
    -0.06
    POSITIVE LOGITS
     بÙĥØ«ÙĬر
    0.08
    mend
    0.08
    èĢĮä¸Ķ
    0.07
    æľī太å¤ļ
    0.07
    argas
    0.07
     hinaus
    0.07
    shed
    0.07
     confines
    0.07
    å¥¢æľĽ
    0.07
    åĵªæĢķ
    0.07
    Activations Density 0.087%

    No Known Activations