© 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. 49952
    Prev
    Next
    INDEX
    Explanations

    .php, .cpp file extensions

    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
    edef
    -0.06
    ede
    -0.06
    人è¦ģ
    -0.06
     esclusiva
    -0.06
    åı¯éĢļè¿ĩ
    -0.06
    own
    -0.06
     exclusiva
    -0.06
    _rep
    -0.06
    为ä»ĸ们
    -0.06
    éĥ½ä¸įè¦ģ
    -0.06
    POSITIVE LOGITS
    åĽłä¸ºæ²¡æľī
    0.10
    hangi
    0.09
     inval
    0.09
    åIJĥåIJĥ
    0.09
    -validate
    0.09
    åħįåĨł
    0.08
    没æľīæī¾åĪ°
    0.08
    ضة
    0.08
    éĢłåĮĸ
    0.08
    ç«£
    0.08
    Activations Density 0.016%

    No Known Activations