© 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. 19088
    Prev
    Next
    INDEX
    Explanations

    date fields and identifiers

    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
    mbH
    -0.07
    ısına
    -0.07
    nés
    -0.07
    人æĦı
    -0.07
    [][]
    -0.07
    áŀ¸
    -0.07
    稼ãģİ
    -0.07
    @m
    -0.07
    errick
    -0.07
    åİļå®ŀ
    -0.07
    POSITIVE LOGITS
    endid
    0.08
    è§Ĩ
    0.07
    ran
    0.07
    stats
    0.07
    ç·´
    0.07
     apro
    0.07
    ebet
    0.07
     whose
    0.07
    enes
    0.06
     dich
    0.06
    Activations Density 0.018%

    No Known Activations