© 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. 18814
    Prev
    Next
    INDEX
    Explanations

    writing to standard output or file

    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
    éĴŁ
    -0.07
    æľĪåĪ°
    -0.07
    неÑĪ
    -0.07
    åĭī强
    -0.07
    身
    -0.07
     Vital
    -0.07
    æľĢè¿ijæĽ´æĸ°
    -0.07
    æľĪä¸Ń
    -0.07
    身çļĦ
    -0.07
    æĹĭ
    -0.07
    POSITIVE LOGITS
    æ
    0.07
     Wiley
    0.06
    rost
    0.06
    纾
    0.06
    æĬ
    0.06
    庶
    0.06
    åĹ£
    0.06
     streams
    0.06
    çĸİ
    0.06
    Streams
    0.06
    Activations Density 0.001%

    No Known Activations