© 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. 21014
    Prev
    Next
    INDEX
    Explanations

    setting values to

    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
    å¢ħ
    -0.07
    åĬĽåĽ¾
    -0.07
    ago
    -0.07
    ICON
    -0.07
    .helpers
    -0.07
    ç»Ļæľĭåıĭ
    -0.07
    chter
    -0.07
    è¸Ĭè·ĥ
    -0.07
    rez
    -0.07
    addle
    -0.06
    POSITIVE LOGITS
    åĢ¼ä¸º
    0.08
    è°ĥ
    0.07
    åħ¨ç¨ĭ
    0.07
    otos
    0.07
    -default
    0.07
    åĢ¼æĺ¯
    0.07
    é»ĺ认
    0.07
    otts
    0.07
    设置为
    0.07
    空
    0.07
    Activations Density 0.083%

    No Known Activations