© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 30079
    Prev
    Next
    INDEX
    Explanations

    numbers or punctuation

    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
    åħ¶å¯¹
    -0.07
    pagen
    -0.07
    éħĭ
    -0.06
    为载ä½ĵ
    -0.06
    -toolbar
    -0.06
    éĩijæ¡¥
    -0.06
    缴æİ¥æĪĸéĹ´æİ¥
    -0.06
    basePath
    -0.06
    smith
    -0.06
    rique
    -0.06
    POSITIVE LOGITS
    è¿Ļæĺ¯ä¸Ģç§į
    0.10
    çIJĨ顺
    0.07
    orias
    0.07
    Ñĸз
    0.07
    ucha
    0.07
    åıįä¹ĭ
    0.07
    管çIJĨæ³ķ
    0.07
    inally
    0.07
    chematic
    0.07
    è¿Ļåľ¨
    0.07
    Activations Density 0.250%

    No Known Activations