© 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. 38224
    Prev
    Next
    INDEX
    Explanations

    special characters and code formatting

    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
    ké
    -0.07
     dispara
    -0.06
    ä»Ģä¹Ī
    -0.06
    ведением
    -0.06
    éķ¿çĽ¸
    -0.06
    åĴĮæĶ¹åĸĦ
    -0.06
    è¾ħ导åijĺ
    -0.05
    hop
    -0.05
     shifted
    -0.05
    .encode
    -0.05
    POSITIVE LOGITS
    itchens
    0.07
    istentes
    0.07
    cola
    0.07
    essin
    0.07
    æīĢ欲è¨Ģ
    0.07
    ',//
    0.07
    olist
    0.07
    ZION
    0.07
    mploy
    0.07
    ỤC
    0.07
    Activations Density 0.067%

    No Known Activations