© 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. 24465
    Prev
    Next
    INDEX
    Explanations

    prime factors or hardware specifications

    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
    ulam
    -0.08
    +</
    -0.08
    outers
    -0.08
    +S
    -0.07
    +W
    -0.07
    åĴĮæĶ¹è¿Ľ
    -0.07
    +F
    -0.07
    +C
    -0.07
    èĮĥçķ´
    -0.07
     Bonne
    -0.07
    POSITIVE LOGITS
    ¥
    0.08
    íİĺ
    0.07
    arine
    0.07
    Å¡in
    0.07
     realtime
    0.07
    à¸ĸ
    0.06
     knack
    0.06
    éĻĦ
    0.06
    jera
    0.06
    à¸Ķิà¸ļ
    0.06
    Activations Density 0.001%

    No Known Activations