© 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. 30702
    Prev
    Next
    INDEX
    Explanations

    inductive step

    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
    åĬ¨çĿĢ
    -0.07
    entas
    -0.06
    ↵
    -0.06
    Next
    -0.06
     First
    -0.06
     Next
    -0.06
    iform
    -0.05
    è¶Ĭ
    -0.05
    re
    -0.05
    elus
    -0.05
    POSITIVE LOGITS
    第ä¸ī个
    0.10
    第ä¸īç§į
    0.09
     third
    0.09
    第ä¸īèĢħ
    0.09
    loh
    0.08
    以å¤ĸãģ¯
    0.08
     اÙĦشر
    0.08
     Tijd
    0.08
    ç¬¬åĽĽä¸ª
    0.08
     thirds
    0.08
    Activations Density 0.244%

    No Known Activations