© 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. 113032
    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
    aggregate
    -0.28
    ets
    -0.27
    ETS
    -0.27
    amac
    -0.26
    åĸĤ
    -0.25
     aggregate
    -0.24
    SYS
    -0.24
    xac
    -0.24
    å°Ĩè¿Ľä¸ĢæŃ¥
    -0.24
    severity
    -0.24
    POSITIVE LOGITS
    -compatible
    0.28
    Means
    0.25
    sen
    0.25
    ÑĮе
    0.24
    宪æ³ķ
    0.24
    家åħ¬åı¸
    0.24
    uffman
    0.23
    .ie
    0.23
     gev
    0.23
    born
    0.23
    Activations Density 0.012%

    No Known Activations

    This feature has no known activations.