© 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. 20985
    Prev
    Next
    INDEX
    Explanations

    construct words using `and`

    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
    ithub
    -0.08
    ative
    -0.07
    éĢļè¿ĩ使çĶ¨
    -0.07
    ise
    -0.06
     intentionally
    -0.06
    ê¸ī
    -0.06
    onian
    -0.06
     desem
    -0.06
    atively
    -0.06
    istiche
    -0.06
    POSITIVE LOGITS
     Spicer
    0.08
    $i
    0.08
    orti
    0.08
    çļĦåIJĦ项
    0.07
    $I
    0.07
    ä¸Ģå¦Ĥ
    0.07
    orto
    0.07
     Sta
    0.07
    宵
    0.07
    ä¼ģä¸ļæľįåĬ¡
    0.07
    Activations Density 0.004%

    No Known Activations