© 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. 65030
    Prev
    Next
    INDEX
    Explanations

    tree hierarchies and lists

    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
    umer
    -0.08
    女åŃIJçļĦ
    -0.06
    ádi
    -0.06
    .toInt
    -0.06
    æİ¥è¿ij尾声
    -0.06
    itty
    -0.06
    emez
    -0.06
    ulton
    -0.06
    ç¼¥
    -0.06
    ryp
    -0.06
    POSITIVE LOGITS
    åĿIJéķĩ
    0.09
    éĵģè¡Ģ
    0.08
    ancar
    0.07
    åıĬåħ¶
    0.07
    Ùħرة
    0.07
    trand
    0.07
    essen
    0.07
    oenix
    0.07
    Æł
    0.07
    enni
    0.07
    Activations Density 0.009%

    No Known Activations