© 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. 29474
    Prev
    Next
    INDEX
    Explanations

    initialization and loops

    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
    çļĦç²¾
    -0.08
    arb
    -0.07
     rispett
    -0.06
    æĢľ
    -0.06
    ç²¾
    -0.06
    éĩĩ
    -0.06
    å¡ŀ
    -0.06
    pj
    -0.06
    åįķ身
    -0.06
    поÑĢа
    -0.06
    POSITIVE LOGITS
    à¤Ĥप
    0.09
    ĥĿ
    0.08
    伦
    0.08
    /npm
    0.08
    leos
    0.08
    astre
    0.08
    /respond
    0.08
    locals
    0.07
    ibold
    0.07
    utsch
    0.07
    Activations Density 0.162%

    No Known Activations