© 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. 23603
    Prev
    Next
    INDEX
    Explanations

    chemical formulas and scientific constants

    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
    åľ¨çº¿çķĻè¨Ģ
    -0.08
    agod
    -0.08
    sker
    -0.08
    inalg
    -0.07
    _deep
    -0.07
    èĭĵ
    -0.07
    bert
    -0.07
    oenix
    -0.06
    æĿİè½»
    -0.06
    æ·±çļĦ
    -0.06
    POSITIVE LOGITS
     molecule
    0.08
    arrer
    0.08
    odus
    0.07
    縼
    0.07
    åij¼åIJ¸
    0.07
     пÑĢока
    0.07
    ä¾Ľæ°Ķ
    0.07
    ç¼Ķ
    0.07
    oci
    0.07
    esz
    0.07
    Activations Density 0.004%

    No Known Activations