© 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. 22871
    Prev
    Next
    INDEX
    Explanations

    copyright notices

    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
    zelfde
    -0.18
    en
    -0.15
    à¦ĩ
    -0.12
    ت
    -0.11
    i
    -0.11
    اء
    -0.11
    ly
    -0.10
    е
    -0.10
    erweise
    -0.10
    м
    -0.10
    POSITIVE LOGITS
    ness
    0.13
    о
    0.10
    als
    0.09
    ings
    0.09
    ishly
    0.09
    itals
    0.09
    oenix
    0.09
    един
    0.08
    ees
    0.08
    sburgh
    0.08
    Activations Density 0.124%

    No Known Activations