© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 7632
    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
     notifyDataSetChanged
    -0.27
    寸
    -0.25
    .BadRequest
    -0.25
    Äħd
    -0.24
    kre
    -0.24
    ev
    -0.24
    fits
    -0.24
    icha
    -0.23
    vendor
    -0.23
    ------+------+
    -0.23
    POSITIVE LOGITS
    åıªæľīä¸Ģ个
    0.27
    ablish
    0.27
    thers
    0.26
    /cpp
    0.26
    /english
    0.25
    é«ĺçŃīåŃ¦æł¡
    0.25
    åħ¶ä»ĸåĽ½å®¶
    0.25
     thereafter
    0.25
     afterward
    0.24
    monic
    0.23
    Activations Density 0.036%

    No Known Activations

    This feature has no known activations.