© 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. 30080
    Prev
    Next
    INDEX
    Explanations

    under one

    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
    ypress
    -0.08
    /Runtime
    -0.07
    nav
    -0.07
    ãģĭãĤĬ
    -0.07
    ÑĤÑĥда
    -0.07
    _DIRECTION
    -0.07
    ypi
    -0.06
    ç§ĺå¯Ĩ
    -0.06
    缨
    -0.06
    -nav
    -0.06
    POSITIVE LOGITS
    engel
    0.07
    igur
    0.06
    éķĩçļĦ
    0.06
    apid
    0.06
    ifax
    0.06
    ick
    0.06
    å½ĵå¹´çļĦ
    0.06
    lement
    0.06
    çĤ¹åĩ»ä¸Ĭæĸ¹
    0.06
     ÙĪترÙĥ
    0.06
    Activations Density 0.001%

    No Known Activations