© 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. 22590
    Prev
    Next
    INDEX
    Explanations

    present invention

    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
    proc
    -0.08
    è·Ŀ
    -0.07
    fc
    -0.07
     Proc
    -0.07
    Proc
    -0.07
    ambi
    -0.07
     proc
    -0.07
    _proc
    -0.06
    acity
    -0.06
     pulled
    -0.06
    POSITIVE LOGITS
    æĸĩçļĦ
    0.08
    .kr
    0.08
    -thumb
    0.08
    _INITIALIZER
    0.07
    åĪĨ享åĪ°æľĭåıĭåľĪ
    0.07
    streams
    0.07
     ìłľ
    0.07
    âĢ¦,
    0.07
    trol
    0.07
     designs
    0.07
    Activations Density 0.228%

    No Known Activations