© 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. 40357
    Prev
    Next
    INDEX
    Explanations

    acknowledgment funding citation

    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
    antu
    -0.07
    æľīæķĪåľ°
    -0.07
    ces
    -0.06
    zep
    -0.06
    沧海
    -0.06
    Ú©Ùħ
    -0.06
    wal
    -0.06
    iosa
    -0.06
    å²ģ以ä¸ĭ
    -0.06
    æĺ¨æĹ¥
    -0.06
    POSITIVE LOGITS
    è¯ĬæĸŃåıĬ
    0.07
    è±ģ
    0.07
    /disable
    0.07
    äºĭå®ľ
    0.07
    壹åı·
    0.07
    èį¼
    0.07
    enders
    0.07
    ä¸Ģå¦Ĥ
    0.06
    .gradle
    0.06
    -all
    0.06
    Activations Density 0.038%

    No Known Activations