© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 61677
    Prev
    Next
    INDEX
    Explanations

    geographic directions and regions

    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
    éĿŀ常好
    -0.07
    èļ¤
    -0.07
    缸åıį
    -0.07
    uppen
    -0.07
    ickey
    -0.07
    ener
    -0.06
     Keeper
    -0.06
    å¼ģ
    -0.06
    æĬ
    -0.06
    éĿŀ常é«ĺ
    -0.06
    POSITIVE LOGITS
    amy
    0.08
     ÙĤÙĦÙĬ
    0.08
     Masih
    0.08
     wp
    0.08
    ónimo
    0.08
    רת
    0.08
    estra
    0.07
    ailing
    0.07
    емо
    0.07
    екÑģи
    0.07
    Activations Density 0.132%

    No Known Activations