© 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. 8471
    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
    eme
    -0.27
    å¯Į
    -0.26
     Intermediate
    -0.26
     DISCLAIMER
    -0.25
    .createParallelGroup
    -0.25
     din
    -0.25
    çĿĽ
    -0.25
     cbo
    -0.24
    ional
    -0.24
    .fn
    -0.24
    POSITIVE LOGITS
    acman
    0.26
    azy
    0.26
    ä¹Łä¸įæĥ³
    0.25
     Raised
    0.25
     porr
    0.25
    tam
    0.25
     Bonds
    0.25
    oud
    0.25
    ä¸įçĶ±å¾Ĺ
    0.25
    át
    0.24
    Activations Density 0.501%

    No Known Activations

    This feature has no known activations.