© 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. 64954
    Prev
    Next
    INDEX
    Explanations

    dates and locations

    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
    æĺĵè´Ń
    -0.08
    lava
    -0.08
    esy
    -0.07
    kog
    -0.07
     overe
    -0.07
    ÙĬÙĦات
    -0.07
    çĽ¸ä¼¼æĸĩçĮ®
    -0.07
    isy
    -0.07
    veu
    -0.07
    æĻºèģĶ
    -0.07
    POSITIVE LOGITS
     come
    0.07
    足
    0.06
    олÑĮ
    0.06
     شاÙĨ
    0.06
     wait
    0.06
    ynch
    0.06
    à¸ķะ
    0.06
    caret
    0.06
    è¿ľ
    0.06
    éĺĻ
    0.06
    Activations Density 0.001%

    No Known Activations