© 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. 63521
    Prev
    Next
    INDEX
    Explanations

    Description of the Related Art

    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
    è¡¡
    -0.07
    åı¨
    -0.06
    ham
    -0.06
     Ghost
    -0.06
    ernen
    -0.06
    oud
    -0.06
    ä¸ĩ人
    -0.06
    ekan
    -0.06
    åįľ
    -0.05
    çĶŁåŃĺ
    -0.05
    POSITIVE LOGITS
    ÙĦÙħÙĬ
    0.08
     sake
    0.08
    åĩºè®©
    0.07
    год
    0.07
    ocol
    0.07
     tá»Ń
    0.07
     Cater
    0.07
    èĦĬæ¢ģ
    0.07
    herits
    0.07
     uninitialized
    0.07
    Activations Density 0.809%

    No Known Activations