© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 58796
    Prev
    Next
    INDEX
    Explanations

    APPEALS FOR THE FIFTH CIRCUIT

    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
    IOC
    -0.08
    注éĶĢå¤ĩæ¡Ī
    -0.08
    ajem
    -0.08
    RITE
    -0.08
    rd
    -0.08
    ημα
    -0.08
    ierungen
    -0.07
    졸
    -0.07
    umentos
    -0.07
    heiten
    -0.07
    POSITIVE LOGITS
     flight
    0.07
     review
    0.07
     cánh
    0.07
    ÙĪÙĨد
    0.07
     reviewing
    0.07
    èģ
    0.06
    iddled
    0.06
     vuelo
    0.06
    à¸ĵà¹Į
    0.06
    ยà¸Ńà¸Ķ
    0.06
    Activations Density 0.323%

    No Known Activations