© 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. 32305
    Prev
    Next
    INDEX
    Explanations

    version numbers or arm architecture

    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
    欣欣
    -0.06
    entr
    -0.06
    eiro
    -0.06
    zzi
    -0.06
    幸ç¦ı
    -0.06
    .unwrap
    -0.06
    entra
    -0.06
    irates
    -0.06
    ä¸ĭåIJĮ
    -0.05
    ระยะ
    -0.05
    POSITIVE LOGITS
    ç«ŀåĵģä¿¡æģ¯
    0.08
    帼
    0.08
    uet
    0.07
    omla
    0.07
    éma
    0.07
    GuidId
    0.07
    unami
    0.07
    主ä½ĵç»ĵæŀĦ
    0.07
    åħĭèĺŃ
    0.07
    eraan
    0.07
    Activations Density 0.020%

    No Known Activations