© 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. 27631
    Prev
    Next
    INDEX
    Explanations

    triple therapy with

    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
    åħŃ大
    -0.06
    è¿Ļ段è¯Ŀ
    -0.06
    olo
    -0.06
    常éĿĴ
    -0.06
     tvr
    -0.06
    è¿Ļä¸Ģ段
    -0.06
    RAR
    -0.06
     à¸Ľà¸£à¸°
    -0.06
    æĭ©
    -0.06
     compromet
    -0.06
    POSITIVE LOGITS
    åĪĨåĪ«
    0.16
    ãģ©ãģ¡ãĤīãĤĤ
    0.16
    åĪĨåĪ«åľ¨
    0.16
     respective
    0.15
     respectively
    0.15
    åĪĨåĪ«ä¸º
    0.14
    è¿Ļ两ç§į
    0.13
    åīįèĢħ
    0.13
    åĪĨåĪ¥
    0.13
    è¿Ļ两款
    0.13
    Activations Density 0.449%

    No Known Activations