© 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. 49285
    Prev
    Next
    INDEX
    Explanations

    sequence of n

    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
    isto
    -0.08
    æµħæµħ
    -0.07
    nga
    -0.07
    ossid
    -0.07
    uther
    -0.07
    ConfigurationException
    -0.07
    æ¯ıä¸Ģ个åѦçĶŁ
    -0.06
    cession
    -0.06
    oure
    -0.06
    ثار
    -0.06
    POSITIVE LOGITS
    itness
    0.08
    è§Ħ模çļĦ
    0.08
     dataSize
    0.08
    ifar
    0.07
    çĶ©
    0.07
     scaling
    0.07
    lez
    0.07
    ekte
    0.07
    venuti
    0.06
     Alv
    0.06
    Activations Density 0.007%

    No Known Activations