© 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. 58130
    Prev
    Next
    INDEX
    Explanations

    latch, flip, circulator, amplifier, transmission gate

    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
    -desktop
    -0.07
    使çĶ¨éģĵåħ·
    -0.07
    StackSize
    -0.07
    缴æݥ被
    -0.07
    oura
    -0.07
    åľ°è¡¨
    -0.07
    èħ¾
    -0.07
    ç§ģ家
    -0.07
    ä½ĵåij³
    -0.07
    æīĭåı¯
    -0.07
    POSITIVE LOGITS
    åĬŁèĥ½çļĦ
    0.11
    åĬŁèĥ½æĺ¯
    0.10
     functionality
    0.10
    åĬŁèĥ½
    0.09
    çļĦåĬŁèĥ½
    0.09
     functioning
    0.09
    çĶ¨éĢĶ
    0.09
     기ëĬ¥ìĿĦ
    0.08
     기ëĬ¥ìĿ´
    0.08
     reversing
    0.08
    Activations Density 0.116%

    No Known Activations