© 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. 9495
    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
     STATES
    -0.25
    uggest
    -0.25
    irs
    -0.25
     Rat
    -0.25
     rat
    -0.25
     applied
    -0.25
    imations
    -0.24
     lượng
    -0.23
     ratified
    -0.23
     joined
    -0.23
    POSITIVE LOGITS
    æħij
    0.28
    StringEncoding
    0.26
    æijĨ
    0.25
    mant
    0.24
     offend
    0.24
    ease
    0.24
     gyr
    0.24
    bery
    0.24
     Appeal
    0.24
     carn
    0.23
    Activations Density 0.001%

    No Known Activations

    This feature has no known activations.