© 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. 113136
    Prev
    Next
    INDEX
    Explanations

    time

    np_max-act · gemini-2.0-flash
    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
    uded
    -0.31
    ÃŃg
    -0.26
    ãģĦãģij
    -0.24
    IRE
    -0.24
    iscrim
    -0.24
    erer
    -0.23
    çŁ¥æĥħ
    -0.23
    atre
    -0.23
    çī¹åĪ«å£°æĺİ
    -0.23
    çľī
    -0.23
    POSITIVE LOGITS
     elapsed
    0.32
    InMillis
    0.30
    .sleep
    0.28
    éķ¿çŁŃ
    0.27
    frame
    0.27
    forces
    0.26
    ä¹ħ
    0.26
     hesitate
    0.26
    _usec
    0.26
     duration
    0.25
    Activations Density 0.200%

    No Known Activations