© 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. 88857
    Prev
    Next
    INDEX
    Explanations

    computer files and programming

    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
    åĪĨ级
    -0.28
    ç½ijé¦ĸ页
    -0.28
    ético
    -0.28
    дов
    -0.27
    scal
    -0.27
    -covered
    -0.26
    â¼
    -0.26
    级
    -0.26
     Cou
    -0.25
    çĨŁæĤī
    -0.25
    POSITIVE LOGITS
     curled
    0.29
    rending
    0.28
     quÃł
    0.25
    -ng
    0.24
    åĮºå§Ķ
    0.24
    unts
    0.24
     sü
    0.23
     +č↵
    0.23
    autiful
    0.23
     counselling
    0.23
    Activations Density 0.001%

    No Known Activations