© 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. 41474
    Prev
    Next
    INDEX
    Explanations

    change THIS HEADER

    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
    鲨
    -0.08
     hoeren
    -0.08
    ondre
    -0.08
    #/
    -0.08
    æĬ±
    -0.07
    æĪijè¦ģè¯Ħ论
    -0.07
    agerie
    -0.07
    apid
    -0.07
    _mgr
    -0.07
    大äºĭ
    -0.07
    POSITIVE LOGITS
     drafts
    0.08
    trak
    0.07
     Draft
    0.07
     draft
    0.06
    ä¸įå¼ĢçļĦ
    0.06
    inger
    0.06
    tering
    0.06
     Trad
    0.06
    rement
    0.06
     Trident
    0.06
    Activations Density 0.001%

    No Known Activations