© 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. 21068
    Prev
    Next
    INDEX
    Explanations

    circuit, certiorari,biological

    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
     segreg
    -0.08
    宫
    -0.07
    czyk
    -0.07
    åĴĮä¸įèī¯
    -0.07
    agma
    -0.07
     Mariana
    -0.07
     اÙĦعط
    -0.07
    æĴij
    -0.07
    insky
    -0.06
    è¯Ħ
    -0.06
    POSITIVE LOGITS
    åħĭåĬĽ
    0.08
    ullo
    0.07
    çĻ½ç¾Ĭ
    0.07
    åĪ¶
    0.06
     circon
    0.06
     (+
    0.06
    ä½ķ为
    0.06
    éĿ¢åIJij
    0.06
    ylv
    0.06
    éĿ¢å¯¹
    0.06
    Activations Density 0.001%

    No Known Activations