© 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. 56192
    Prev
    Next
    INDEX
    Explanations

    adding elements to collections

    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
    ç»ĩ女
    -0.07
    ówki
    -0.07
    æĽ´æĸ°
    -0.07
    çĦķ
    -0.07
    iska
    -0.07
     offsetof
    -0.07
    ower
    -0.07
    ylon
    -0.06
     khoán
    -0.06
    enio
    -0.06
    POSITIVE LOGITS
     tempList
    0.08
    aturi
    0.08
    å¿«éĢŁå¢ŀéķ¿
    0.08
    adding
    0.08
    å·¥ä½ľç»ıåİĨ
    0.07
    .addObject
    0.07
     contrac
    0.07
    append
    0.07
    éķ¿çº¦
    0.07
    élé
    0.07
    Activations Density 0.030%

    No Known Activations