© 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. 40229
    Prev
    Next
    INDEX
    Explanations

    over a field

    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
    çĸ½
    -0.07
    yb
    -0.06
     spir
    -0.06
    ose
    -0.06
    æ´²
    -0.06
    UNA
    -0.06
    oria
    -0.06
    гÑĢам
    -0.06
    ÙĨÛĮÙĨ
    -0.06
     Kumar
    -0.06
    POSITIVE LOGITS
    heck
    0.08
    leck
    0.08
    ÑĢом
    0.07
    úng
    0.07
    åŁºçĤ¹
    0.07
    OPS
    0.07
    abet
    0.07
    -support
    0.07
    attel
    0.07
    ведением
    0.07
    Activations Density 0.008%

    No Known Activations