© 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. 47820
    Prev
    Next
    INDEX
    Explanations

    building, health, digital, cardiac, clinical, adip, software, finance, bathrooms, transplantation

    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
    chè
    -0.08
    åĴĮèĥ½åĬĽ
    -0.08
    urations
    -0.07
    lagen
    -0.07
     Peker
    -0.07
    éĺ¶æ®µæĢ§
    -0.07
    un
    -0.07
    天ä¸ĭ第ä¸Ģ
    -0.07
    åĴĮæĸ¹æ³ķ
    -0.07
    人æĪĸ
    -0.07
    POSITIVE LOGITS
    åĸľæ¬¢ä½ł
    0.07
     including
    0.07
    æīĢéľĢè¦ģçļĦ
    0.07
    åŁºç¡ĢçŁ¥è¯Ĩ
    0.07
    æīĢéľĢçļĦ
    0.07
    çļĦåIJĦ项
    0.07
    angk
    0.07
    ÙĪÙĬÙĦ
    0.07
    åŁºæľ¬çŁ¥è¯Ĩ
    0.06
    æĪijåľ¨è¿ĻéĩĮ
    0.06
    Activations Density 0.183%

    No Known Activations