© 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. 63068
    Prev
    Next
    INDEX
    Explanations

    tracks coordinates of links

    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
    æľīåħ³äººåijĺ
    -0.07
    unden
    -0.06
    è·µ
    -0.06
    WithMany
    -0.06
    èĭ¥å¹²éĹ®é¢ĺçļĦ
    -0.06
    çłĶ究ä¸İ
    -0.06
    纫
    -0.06
    __$
    -0.06
    çİ°çĬ¶åıĬ
    -0.06
    omi
    -0.06
    POSITIVE LOGITS
    é»ijæļĹçļĦ
    0.08
    üy
    0.08
    çĶ·ç¥ŀ
    0.08
     legacy
    0.07
    nes
    0.07
    iless
    0.07
    åįİ西
    0.07
    .ms
    0.07
    åѦäºĨ
    0.07
    ÅĤu
    0.07
    Activations Density 0.151%

    No Known Activations