© 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. 24444
    Prev
    Next
    INDEX
    Explanations

    decompress or decompose

    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
    -0.11
    ifacts
    -0.08
    zinho
    -0.08
    atures
    -0.08
    oplevel
    -0.08
    engeb
    -0.08
    åľ¨æŀĹ
    -0.08
    ©
    -0.08
    à¹Ģà¸Ķีย
    -0.08
    ī
    -0.08
    POSITIVE LOGITS
    ÑģÑı
    0.11
    plin
    0.10
    ósito
    0.08
    /dis
    0.08
    o
    0.08
    ب
    0.08
    /div
    0.08
    ly
    0.08
    ات
    0.08
    er
    0.08
    Activations Density 0.005%

    No Known Activations