© 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. 2627
    Prev
    Next
    INDEX
    Explanations

    list of data

    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
    è¡¡
    -0.07
    ä¸ŃåĴĮ
    -0.07
    tide
    -0.07
    uste
    -0.06
    _BUSY
    -0.06
    aub
    -0.06
     mosa
    -0.06
    èĻ½çĦ¶åľ¨
    -0.06
     rejoindre
    -0.06
     Andres
    -0.06
    POSITIVE LOGITS
    zt
    0.08
    enz
    0.08
    éľĢæ±Ĥ
    0.08
    大ä¸Ń
    0.08
    sville
    0.07
    raw
    0.07
    çīĪæĿĥæīĢæľī
    0.07
    .Raw
    0.07
    zut
    0.07
    _domains
    0.07
    Activations Density 0.903%

    No Known Activations