© 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. 38879
    Prev
    Next
    INDEX
    Explanations

    WITHOUT ANY WARRANTY

    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
    说åĪ°è¿ĻéĩĮ
    -0.08
     basename
    -0.08
    baum
    -0.08
    udit
    -0.07
    ave
    -0.07
     Vog
    -0.07
    çĶľèľľçļĦ
    -0.07
    Ãły
    -0.07
    延ç¼ĵ
    -0.07
    imes
    -0.07
    POSITIVE LOGITS
     اÙĦصØŃ
    0.06
    åĪ©
    0.06
     fac
    0.06
    oglio
    0.06
     lessons
    0.06
    ç¨ĭ度ä¸Ĭ
    0.06
    ÃŃnio
    0.06
    *((
    0.06
    'Connor
    0.06
    agged
    0.06
    Activations Density 0.011%

    No Known Activations