© 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. 19524
    Prev
    Next
    INDEX
    Explanations

    UTSTARCOM, pursuit, JUJU, LU

    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
    ãĤħãģĨ
    -0.09
    ä¸įæ¸Ŀ
    -0.08
     ÑĥÑģÑĸ
    -0.07
     lẽ
    -0.07
    ensive
    -0.07
    åħ³æĿij
    -0.07
    mony
    -0.07
    ldr
    -0.07
    itudine
    -0.07
    ëĵ¬
    -0.07
    POSITIVE LOGITS
    Ñģловно
    0.12
    ÑĤÑĢеннÑıÑı
    0.12
    λάÏĩιÏĥ
    0.11
     بÙĴÙĨÙı
    0.11
    mehr
    0.11
    endlich
    0.10
    ltra
    0.10
    нивеÑĢ
    0.10
    dür
    0.10
     οÏĢοί
    0.10
    Activations Density 2.669%

    No Known Activations