© 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. 33554
    Prev
    Next
    INDEX
    Explanations

    Adam and Eve

    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
    kira
    -0.07
     Belle
    -0.07
    声åĬ¿
    -0.07
    ä¸įå®ļæľŁ
    -0.07
    åĭŁ
    -0.07
    ä¸Ģè·¯
    -0.07
    eya
    -0.07
     aggressively
    -0.07
    øj
    -0.07
     haystack
    -0.07
    POSITIVE LOGITS
     Homo
    0.08
    å§ĭç¥ĸ
    0.08
    ankind
    0.07
    第ä¸Ģ课
    0.07
     Eve
    0.07
     mankind
    0.07
     disobed
    0.07
    èĥļ
    0.07
    ç¾ŀ
    0.07
    quam
    0.07
    Activations Density 0.016%

    No Known Activations