© 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. 29784
    Prev
    Next
    INDEX
    Explanations

    unchanged or remained the same over years

    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
    andra
    -0.07
    åıİ
    -0.07
    å¿ĥæĤ¦
    -0.07
    veni
    -0.06
    eder
    -0.06
    åĩ°
    -0.06
    erien
    -0.06
    iences
    -0.06
    awa
    -0.06
    çļĻ
    -0.06
    POSITIVE LOGITS
     unchanged
    0.15
    ä¸įåıĺçļĦ
    0.14
    ä¸įåıĺ
    0.14
    ä¿ĿæĮģä¸įåıĺ
    0.13
    ä¸įåĬ¨
    0.11
    ä¿ĿæĮģ稳å®ļ
    0.11
    ä¸įè®Ĭ
    0.11
    ç»´æĮģ
    0.11
     maintained
    0.11
    ç»´æĮģåľ¨
    0.10
    Activations Density 0.067%

    No Known Activations