© 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. Qwen3-4B
    5. 22-TRANSCODER-HP
    7. 97102
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     sv
    -0.26
    singular
    -0.24
    isObject
    -0.24
     sing
    -0.24
    _singular
    -0.24
     stri
    -0.24
    (sv
    -0.24
    å°ijéĩı
    -0.24
     singular
    -0.23
     Svens
    -0.23
    POSITIVE LOGITS
     antic
    0.31
    iculos
    0.31
    ä»Ģä¹Īåij¢
    0.28
    æĬĬå®ĥ
    0.27
    enderror
    0.25
    çļĦçĶ»éĿ¢
    0.25
    ueur
    0.24
    好åIJĹ
    0.24
    izontal
    0.24
    .timeScale
    0.24
    Activations Density 0.004%

    No Known Activations

    This feature has no known activations.