© 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. 13616
    Prev
    Next
    INDEX
    Explanations

    symbiotic relationships, symbiosis, endosymbionts

    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
    ostat
    -0.08
    acos
    -0.08
    aset
    -0.07
    è¯ķæİ¢
    -0.07
    èĥ
    -0.07
    æĭīå¼ĢäºĨ
    -0.06
    DOS
    -0.06
    çĪµ
    -0.06
    æŁļ
    -0.06
    tare
    -0.06
    POSITIVE LOGITS
     symb
    0.14
    åħ±çĶŁ
    0.12
    åIJĪä½ľçļĦ
    0.10
    深度åIJĪä½ľ
    0.10
    çļĦåIJĪä½ľ
    0.09
    äºĴåĪ©
    0.09
    åIJĪä½ľåħ³ç³»
    0.09
     partnership
    0.09
    宿主
    0.09
    åħ¥é©»
    0.09
    Activations Density 0.041%

    No Known Activations