© 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. 99122
    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
    è¹Ħ
    -0.28
    еле
    -0.26
     yı
    -0.26
    çĹķ
    -0.26
    çŁ³åĮĸ
    -0.25
    [*
    -0.25
    [--
    -0.24
    uron
    -0.24
    erase
    -0.24
    ibraries
    -0.23
    POSITIVE LOGITS
    PW
    0.28
    oby
    0.27
     Dob
    0.27
    GOR
    0.26
     PW
    0.25
    Mount
    0.25
    -BEGIN
    0.25
    ãĥĬãĥ³
    0.25
    dfd
    0.24
    Pu
    0.24
    Activations Density 0.013%

    No Known Activations

    This feature has no known activations.