© 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. 44998
    Prev
    Next
    INDEX
    Explanations

    conquistadors, National Congress, Saud, American Revolution, Revolutionary War, Bruce, Liberation Organization

    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
    ä¸Ń磩
    -0.07
    ä¼łåĶ¤
    -0.07
    太å®Ī
    -0.07
    çªĴ
    -0.07
    Äħcz
    -0.06
    å¾Ģ常ä¸Ģæł·
    -0.06
    åħ¬å®īåĪĨå±Ģ
    -0.06
    åŀ£
    -0.06
    باط
    -0.06
    wich
    -0.06
    POSITIVE LOGITS
     conquest
    0.11
    æĪIJåĬŁåIJİ
    0.10
    åıijå±ķ壮大
    0.10
    Bootstrap
    0.10
     завое
    0.10
     conqu
    0.09
    å»ºåĽ½
    0.09
    çĻ¾æĪĺ
    0.08
    夺åıĸ
    0.08
     bootstrap
    0.08
    Activations Density 0.092%

    No Known Activations