© 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. 41144
    Prev
    Next
    INDEX
    Explanations

    phrase titles

    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
    ingly
    -0.06
    à¸Ľà¸£à¸°à¸ģัà¸Ļ
    -0.06
    ilot
    -0.06
    åIJĮåľ¨
    -0.06
     additional
    -0.06
    ä¸įèĤ¯
    -0.06
    åıĪå¦Ĥ
    -0.06
    å¸ĤæĶ¿åħ¬çĶ¨
    -0.06
    apatos
    -0.06
    ãģĿãģĨãģ§
    -0.06
    POSITIVE LOGITS
    KHR
    0.08
    ptos
    0.07
    udan
    0.07
    hors
    0.07
    aal
    0.07
    alogy
    0.07
    ÑģÑı
    0.07
    äºĨèµ·æĿ¥
    0.07
    (KP
    0.07
    è¨Ģä¹ĭ
    0.07
    Activations Density 0.001%

    No Known Activations