© 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. 38784
    Prev
    Next
    INDEX
    Explanations

    Indiana court documents

    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
     evid
    -0.08
     emphas
    -0.07
    ised
    -0.07
    оÑģÑĥ
    -0.07
     recognised
    -0.07
     favour
    -0.07
    arrow
    -0.07
     underlying
    -0.07
    olics
    -0.07
    å¦Ĥä¸Ĭ
    -0.06
    POSITIVE LOGITS
    çĤ¹æѤ
    0.07
     (*((
    0.07
    )(__
    0.07
    =sys
    0.07
     sogenannten
    0.07
    以ä¸ĭç®Ģ称
    0.07
    Ø·ØŃ
    0.06
    cntl
    0.06
    inke
    0.06
    %B
    0.06
    Activations Density 0.002%

    No Known Activations