© 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. 56992
    Prev
    Next
    INDEX
    Explanations

    geographical locations and proper nouns

    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
     either
    -0.07
    Âł
    -0.06
    ...
    -0.06
    oci
    -0.06
     /
    -0.06
     -
    -0.06
     whichever
    -0.06
    ä¸Ķ
    -0.06
    æĺĤ
    -0.06
    0
    -0.06
    POSITIVE LOGITS
    hô
    0.09
    bÃŃ
    0.08
    æī©å±ķèµĦæĸĻ
    0.08
    ابÙĩ
    0.08
     minlength
    0.08
    cba
    0.08
    åĭĴæĸ¯
    0.08
    azzo
    0.08
    .memo
    0.08
    oghi
    0.08
    Activations Density 0.007%

    No Known Activations