© 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. 38410
    Prev
    Next
    INDEX
    Explanations

    mathematical notation

    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
    åıijå±ķä¸İ
    -0.07
    丼çĶŁ
    -0.07
    è¿ĻäºĽéĹ®é¢ĺ
    -0.07
     Biel
    -0.06
    è¿Ļæł·çļĦéĹ®é¢ĺ
    -0.06
    quil
    -0.06
     algu
    -0.06
    stel
    -0.06
    development
    -0.06
    åħĪåİ»
    -0.06
    POSITIVE LOGITS
    Normalized
    0.08
    HCI
    0.08
     Herc
    0.08
     acos
    0.08
    iane
    0.08
    PCS
    0.08
    Mt
    0.07
     дÑĥ
    0.07
     normalized
    0.07
     cosine
    0.07
    Activations Density 0.003%

    No Known Activations