© 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. 60599
    Prev
    Next
    INDEX
    Explanations

    numbers followed by units or identifiers

    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
    åįģåĪĨéĩįè¦ģ
    -0.08
    ä¹ĭåıĪ
    -0.08
    uzzi
    -0.08
    åıĪä½ķ
    -0.07
    izona
    -0.07
    ansen
    -0.07
    åľºæīĢ
    -0.07
    áng
    -0.07
    blr
    -0.07
    stal
    -0.07
    POSITIVE LOGITS
    åĽ½éģĵ
    0.08
    ë²Ī
    0.08
    ï¸İ
    0.07
    itary
    0.07
    ÙĨدÙĩ
    0.06
     |_|
    0.06
    igne
    0.06
    .addObject
    0.06
    åįĹåĽ½
    0.06
    ignes
    0.06
    Activations Density 0.365%

    No Known Activations