© 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. 110948
    Prev
    Next
    INDEX
    Explanations

    URLs and code

    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
     **
    -0.28
     Unique
    -0.26
     Mission
    -0.26
     Fields
    -0.25
    ACITY
    -0.24
    ener
    -0.24
    itudes
    -0.24
    -West
    -0.24
     Du
    -0.23
    使åij½
    -0.23
    POSITIVE LOGITS
     apparent
    0.25
     msm
    0.25
    å¼ķè¿Ľ
    0.25
    交èѦ
    0.24
    åħ¬å®īéĥ¨
    0.24
    è¢«åĽ°
    0.24
    antro
    0.24
    otp
    0.23
     uniform
    0.23
     sideways
    0.23
    Activations Density 0.239%

    No Known Activations