© 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. 25679
    Prev
    Next
    INDEX
    Explanations

    rooted devices

    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
    berger
    -0.08
    éļ¾å¾ĹçļĦ
    -0.07
    çī©ä»·
    -0.07
    OOD
    -0.07
    æ°ĵ
    -0.07
    kiye
    -0.06
    aret
    -0.06
    anship
    -0.06
    æľīæľº
    -0.06
     möglichst
    -0.06
    POSITIVE LOGITS
    æīįåı¯ä»¥
    0.08
    转载请注æĺİåĩºå¤Ħ
    0.08
    etu
    0.08
    缸åħ³ä¼ģä¸ļ
    0.07
    æīįèĥ½å¾ĹåĪ°
    0.07
    她æīį
    0.07
    edith
    0.07
    åı¯ä¸º
    0.07
    好åIJ§
    0.07
    ouz
    0.07
    Activations Density 0.106%

    No Known Activations