© 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. 43032
    Prev
    Next
    INDEX
    Explanations

    current addition or leakage

    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
    eil
    -0.07
    æľ
    -0.07
    obr
    -0.07
    åħĥç´łçļĦ
    -0.07
     Loot
    -0.07
     mél
    -0.06
     гÑĥманиÑĤаÑĢ
    -0.06
    _BP
    -0.06
    oku
    -0.06
    ilon
    -0.06
    POSITIVE LOGITS
     trickle
    0.09
    æ¼ı
    0.08
     leak
    0.08
    æµģè¿ĩ
    0.08
    åĢįå¢ŀ
    0.08
    äºĮæŀģ管
    0.08
    æİĸ
    0.08
    adders
    0.08
     leakage
    0.08
    ACTIVE
    0.07
    Activations Density 0.013%

    No Known Activations