© 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
    2. Qwen3.5-9B Base
    3. 15-QWENSCOPE-RES-64K
    4. 4524
    Prev
    Next
    INDEX
    Explanations

    comprehensive proposal

    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
     “
    -0.12
    ’
    -0.10
     (“
    -0.09
    Âł
    -0.09
     toward
    -0.09
    âĢij
    -0.09
    “
    -0.08
    –
    -0.08
    ’ll
    -0.08
    âĢ
    -0.08
    POSITIVE LOGITS
    'm
    0.11
     renowned
    0.08
    สà¸ĩ
    0.08
    arán
    0.08
    ),'
    0.08
     '
    0.08
    ).[
    0.08
     **'
    0.08
     swiftly
    0.08
     meticulously
    0.08
    Activations Density 0.010%

    No Known Activations