© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 14566
    Prev
    Next
    INDEX
    Explanations

    blob/master file paths

    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
    apot
    -0.08
    akit
    -0.07
    Ac
    -0.07
    alog
    -0.07
    atak
    -0.07
     brows
    -0.07
    acun
    -0.07
    isku
    -0.07
    emény
    -0.07
    ustr
    -0.07
    POSITIVE LOGITS
    anders
    0.07
    ä¸įæ¸Ŀ
    0.07
    å½ĵä»ĸ们
    0.07
    okra
    0.06
    ulta
    0.06
    inous
    0.06
    perimental
    0.06
    anee
    0.06
    arne
    0.06
     pierced
    0.06
    Activations Density 0.051%

    No Known Activations