© 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. 30059
    Prev
    Next
    INDEX
    Explanations

    integers, variables, and constants

    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
    为主导
    -0.08
    ä»»ä¸Ģ
    -0.08
    严äºİ
    -0.08
    ä¸ĭåĨ³å¿ĥ
    -0.07
    KeyDown
    -0.07
    å··
    -0.07
    ä¿Ŀå®Ī
    -0.07
    大年
    -0.07
    为主çļĦ
    -0.07
     conservative
    -0.07
    POSITIVE LOGITS
    åıĬ设å¤ĩ
    0.07
    è¿Ļ个女人
    0.07
    abar
    0.07
    ÃŃze
    0.06
    页æķ°
    0.06
    ocas
    0.06
    ê¸ī
    0.06
    åı½åı½
    0.06
    eix
    0.06
     value
    0.06
    Activations Density 0.009%

    No Known Activations