© 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. 1132
    Prev
    Next
    INDEX
    Explanations

    color darker

    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
     minlength
    -0.08
    avas
    -0.07
    ingi
    -0.07
    æ¸ħæ¥ļçļĦ
    -0.07
    itan
    -0.07
     **:**
    -0.06
    解åĨ³
    -0.06
    æĥľ
    -0.06
    é¢Ĩ
    -0.06
    egd
    -0.06
    POSITIVE LOGITS
    roids
    0.07
     پرد
    0.07
    æľī人认为
    0.07
    پرد
    0.07
    åĴĮè¡ĮåĬ¨
    0.07
    /disc
    0.07
    åĩłå£°
    0.07
    orsch
    0.07
    orts
    0.06
    çłĶ究åijĺ
    0.06
    Activations Density 0.001%

    No Known Activations