© 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. 7614
    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
     Trinidad
    -0.26
    èĮ«èĮ«
    -0.26
    ĸī
    -0.25
    ledge
    -0.24
     Compiled
    -0.24
     totaled
    -0.24
    _NAMESPACE
    -0.22
     distressed
    -0.22
     Wyn
    -0.22
    _stdout
    -0.21
    POSITIVE LOGITS
    äºīåıĸ
    0.25
    .cc
    0.23
    ÅĽcie
    0.23
    .pl
    0.23
    oppers
    0.23
    earing
    0.22
    èĬĤ约
    0.22
    å¾Īæ·±
    0.22
    )?$
    0.22
     dent
    0.21
    Activations Density 0.107%

    No Known Activations

    This feature has no known activations.