© 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. 112989
    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
    das
    -0.24
    ree
    -0.24
    -I
    -0.24
     Pers
    -0.23
     construct
    -0.23
    æĭĽåķĨå¼ķ
    -0.23
    óa
    -0.23
     identities
    -0.22
    å·²ç»ıè¾¾åĪ°
    -0.22
    nob
    -0.22
    POSITIVE LOGITS
    (TM
    0.25
    cers
    0.25
     Appe
    0.25
    æľªçŁ¥
    0.25
     procur
    0.25
    pollo
    0.25
     Conan
    0.25
    详è§ģ
    0.24
    :index
    0.23
    éªĨ
    0.23
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.