© 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. 8883
    Prev
    Next
    INDEX
    Explanations

    biological and technical subjects

    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
    ArrayOf
    -0.07
    ctest
    -0.07
    amani
    -0.06
    urras
    -0.06
    ẩn
    -0.06
    maal
    -0.06
    -Speed
    -0.06
    åħ¶çī¹å¾ģ
    -0.06
    _unpack
    -0.06
    aeper
    -0.06
    POSITIVE LOGITS
    -specific
    0.11
    æľ¬èº«çļĦ
    0.09
    -wide
    0.09
    /people
    0.08
    mate
    0.08
    å°ıçļĦæŶåĢĻ
    0.08
    èĢĮæĺ¯åĽłä¸º
    0.08
    -level
    0.07
    /team
    0.07
    -induced
    0.07
    Activations Density 0.318%

    No Known Activations