© 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. 51779
    Prev
    Next
    INDEX
    Explanations

    numbers and connections

    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
    uster
    -0.09
    USTER
    -0.07
     Nhĩ
    -0.07
    æĹłæĦıä¸Ń
    -0.07
    anan
    -0.07
    plain
    -0.07
    esine
    -0.07
    $body
    -0.07
    cee
    -0.07
    CEE
    -0.07
    POSITIVE LOGITS
    shots
    0.07
    éĻħ
    0.07
    ÏĢι
    0.07
    .slides
    0.07
    .Feature
    0.07
    Ø´ÙĪ
    0.06
    åħįè´¹åıijå¸ĥ
    0.06
    гда
    0.06
    æŁ³å·ŀ
    0.06
    isir
    0.06
    Activations Density 0.004%

    No Known Activations