© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 8510
    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
    Not in Any Lists

    No Comments

    Negative Logits
    setLayout
    -0.28
    inel
    -0.27
    afort
    -0.26
    棹
    -0.26
     fg
    -0.26
    æĨĶ
    -0.25
    above
    -0.24
    accom
    -0.24
     friction
    -0.23
     infinitely
    -0.23
    POSITIVE LOGITS
    ilog
    0.27
    延ç»Ń
    0.26
    å¾Īéĩįè¦ģ
    0.25
    ector
    0.25
    Declare
    0.24
    TestData
    0.24
     Logistic
    0.24
     Canberra
    0.23
    ucid
    0.23
    alcon
    0.23
    Activations Density 0.240%

    No Known Activations

    This feature has no known activations.