© 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. 41347
    Prev
    Next
    INDEX
    Explanations

    Input/Output activity

    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
    ahu
    -0.08
    izen
    -0.08
    ither
    -0.08
    ÙĪÙĨÛĮ
    -0.08
    urger
    -0.08
    akarta
    -0.08
    +xml
    -0.07
    ingin
    -0.07
    ÙĪÙĨØ©
    -0.07
    ENE
    -0.07
    POSITIVE LOGITS
    æĪijèĩª
    0.06
    озна
    0.06
    rozen
    0.06
    ç»Ŀ对çļĦ
    0.06
    é£İäºij
    0.06
    оÑī
    0.05
    icone
    0.05
    åĨ
    0.05
    Ñīи
    0.05
    તા
    0.05
    Activations Density 0.854%

    No Known Activations