© 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. 10184
    Prev
    Next
    INDEX
    Explanations

    array changes

    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
    è¶Ĭéķ¿
    -0.07
    .gov
    -0.07
    abschluss
    -0.07
    è¶Ĭ强
    -0.07
     Dunk
    -0.07
    .TryParse
    -0.07
    chetto
    -0.06
    legen
    -0.06
    éľĢè¦ģæıIJä¾Ľ
    -0.06
    oka
    -0.06
    POSITIVE LOGITS
     changes
    0.09
    å±Ģéĥ¨
    0.08
    swap
    0.08
    åĨįæĬĬ
    0.07
     изменений
    0.07
    æĶ¹åıĺçļĦ
    0.07
     rearr
    0.07
    åĨįçĤ¹åĩ»
    0.07
    檬
    0.07
    æĶ¹åıĺäºĨ
    0.07
    Activations Density 0.017%

    No Known Activations