© 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. 1994
    Prev
    Next
    INDEX
    Explanations

    clear, concise, well-written

    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
    HEN
    -0.07
    帯
    -0.07
    ä¸ĸäºĭ
    -0.07
     Pruitt
    -0.07
    å°ıè§ij
    -0.07
    æĽ´åħ¨
    -0.07
    ä¸ĢèģĬ
    -0.07
    ä¸įå°½
    -0.07
    çĮĽ
    -0.07
    _APPS
    -0.06
    POSITIVE LOGITS
     luc
    0.08
    æĿ¡çIJĨ
    0.08
     concise
    0.07
     clearly
    0.07
    мп
    0.07
    juan
    0.07
     Mois
    0.07
    è¡Įæĸĩ
    0.06
    æĺ¯ç¾İåĽ½
    0.06
     clarity
    0.06
    Activations Density 0.008%

    No Known Activations