© 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. 51769
    Prev
    Next
    INDEX
    Explanations

    identify, determine, rely, trust, view, have, spot, find

    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
    让çݩ家
    -0.08
    让
    -0.08
     farlo
    -0.08
    让å®ĥ们
    -0.07
    让åIJĮåѦ们
    -0.07
    åį´è®©
    -0.07
    人å¿ĥçļĦ
    -0.07
    @qq
    -0.07
    æīįèĥ½è®©
    -0.07
    issons
    -0.07
    POSITIVE LOGITS
    被åijĬçŁ¥
    0.10
    ä»ĸ们æīĢ
    0.09
    å¦Ĥæŀľä»ĸ们
    0.09
    èİ·çĽĬ
    0.08
    ä¼ļè§īå¾Ĺ
    0.08
     terecht
    0.08
    æĦŁåıĹåĪ°
    0.08
    æīijéĿ¢
    0.08
     receive
    0.08
    åľ¨ä»ĸ们çļĦ
    0.07
    Activations Density 0.435%

    No Known Activations