© 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. 19-TRANSCODER-HP
    7. 9606
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    ismo
    -0.31
    ạy
    -0.29
    agrams
    -0.27
    /sm
    -0.26
    积
    -0.26
    ãĥ½
    -0.26
    ÑĩÑĥ
    -0.26
    istro
    -0.25
    伸
    -0.25
    å±ķ
    -0.25
    POSITIVE LOGITS
    ÙĪاÙĨ
    0.29
    iless
    0.25
    INET
    0.25
    è´£ç¼ĸ
    0.24
     familial
    0.23
     anale
    0.23
    -valid
    0.23
     FXMLLoader
    0.23
     ComponentFixture
    0.23
     Âł Âł Âł Âł
    0.23
    Activations Density 0.032%

    No Known Activations

    This feature has no known activations.