© 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. 21433
    Prev
    Next
    INDEX
    Explanations

    real numbers and vectors

    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
    zyb
    -0.09
    çIJĨ论水平
    -0.09
    æ¯Ķèĩªå·±
    -0.08
    enville
    -0.08
    cff
    -0.08
     Grie
    -0.08
     Thrones
    -0.08
    窿
    -0.08
     !_
    -0.08
    werb
    -0.08
    POSITIVE LOGITS
    çīĪçļĦ
    0.07
    oreal
    0.07
    çīĪ
    0.07
    ued
    0.06
     Jos
    0.06
     version
    0.06
    èĨ
    0.06
    çīĪæľ¬
    0.06
    -only
    0.06
    éĵ¸å°±
    0.06
    Activations Density 0.008%

    No Known Activations