© 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. 31264
    Prev
    Next
    INDEX
    Explanations

    mathematical statements

    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
    约翰éĢĬ
    -0.08
    _commands
    -0.08
    åij¨è½¬
    -0.07
    ellem
    -0.07
    计ç®Ĺæĸ¹æ³ķ
    -0.07
    rawl
    -0.07
    è½®åĪ°
    -0.07
     kräf
    -0.07
    .website
    -0.07
    éĿ¢åIJij
    -0.07
    POSITIVE LOGITS
     restrictive
    0.08
    åĽłä¸ºåıªæľī
    0.08
    æĺ¯åĶ¯ä¸Ģ
    0.07
    åĪ°ä¸Ń
    0.07
     stricter
    0.07
    .Restr
    0.07
    æīįèĥ½å¾ĹåĪ°
    0.07
    za
    0.07
    æīįèĥ½ä½¿
    0.07
     Otherwise
    0.07
    Activations Density 0.008%

    No Known Activations