© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 16292
    Prev
    Next
    INDEX
    Explanations

    human person or being

    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
    hea
    -0.08
    微信æī«çłģ
    -0.07
    anter
    -0.07
     bersifat
    -0.07
     mim
    -0.07
    halen
    -0.07
    å®ĥ对
    -0.07
    uiltin
    -0.07
    lag
    -0.07
    ulg
    -0.07
    POSITIVE LOGITS
    å°Ĭ严
    0.08
    enzi
    0.08
    bow
    0.07
    æľīåĪ«
    0.07
    çļĦä¸Ģåijĺ
    0.07
     individ
    0.07
     dignity
    0.07
    ç£ĭ
    0.07
     mere
    0.07
     integ
    0.07
    Activations Density 0.079%

    No Known Activations