© 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. 46685
    Prev
    Next
    INDEX
    Explanations

    collimated, parallel, rays

    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
    fully
    -0.08
    yen
    -0.08
    fulness
    -0.07
    ful
    -0.07
    ç»´
    -0.07
    Ñĩив
    -0.07
     Bloody
    -0.06
    éĹ°
    -0.06
    adero
    -0.06
     comple
    -0.06
    POSITIVE LOGITS
    incoming
    0.08
    æĪĸèĢħæľī
    0.08
    igid
    0.07
    å°Ħ
    0.07
     rays
    0.07
    éĽ
    0.07
    ´Ģ
    0.07
    ilter
    0.07
    zheimer
    0.07
    .xhtml
    0.07
    Activations Density 0.001%

    No Known Activations