© 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. 39459
    Prev
    Next
    INDEX
    Explanations

    code snippets or questions

    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
     (“
    -0.07
    ange
    -0.07
    äºĮèĢħ
    -0.07
    auge
    -0.06
    iger
    -0.06
    两èĢħ
    -0.06
     Yok
    -0.06
    ings
    -0.06
    tii
    -0.06
    ihal
    -0.06
    POSITIVE LOGITS
    ëŀ
    0.08
    éļĪ
    0.08
    çĴĢ
    0.08
    大éĥ¨åĪĨçļĦ
    0.08
    bpp
    0.08
    bito
    0.07
    æľīå¾Īå¤ļçļĦ
    0.07
    obo
    0.07
    è¦ģè·Ł
    0.07
    STRUCTOR
    0.07
    Activations Density 0.007%

    No Known Activations