© 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. 21693
    Prev
    Next
    INDEX
    Explanations

    genetic knockout mutants

    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
    usc
    -0.07
     dét
    -0.07
    atu
    -0.07
    åħŃéģĵ
    -0.06
    assage
    -0.06
    æŬ
    -0.06
    人å¿ĥçļĦ
    -0.06
    parate
    -0.06
    achine
    -0.06
    åIJ¸å¼ķåĬĽ
    -0.06
    POSITIVE LOGITS
    Balancer
    0.08
    å®ŀéªĮåŃ¦æł¡
    0.08
    ç¦ģ
    0.08
     knock
    0.07
     experiments
    0.07
     deaf
    0.07
    CHIP
    0.07
    elte
    0.07
     tapp
    0.07
    /rem
    0.07
    Activations Density 0.226%

    No Known Activations