© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 22573
    Prev
    Next
    INDEX
    Explanations

    people in need

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/qwen-3.5-saes/qwen-3.5-4b
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    äºĭ
    -0.06
    諦
    -0.06
    ahr
    -0.06
    å®īåħ¨
    -0.05
    大éĩı
    -0.05
    ä¿ĿæĮģä¸įåıĺ
    -0.05
     boh
    -0.05
    inter
    -0.05
    vr
    -0.05
    åIJĪæ³ķ
    -0.05
    POSITIVE LOGITS
     unsus
    0.06
     pronta
    0.06
    人åĿĩåı¯
    0.06
     therein
    0.05
     sẵn
    0.05
     hooked
    0.05
    jadi
    0.05
    eprom
    0.05
    _ready
    0.05
     amongst
    0.05
    Activations Density 0.009%

    No Known Activations