© 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. 8368
    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
    otte
    -0.28
    åĨį
    -0.25
     osob
    -0.25
    讵
    -0.25
    åĿª
    -0.24
    å°±æĺ¯åľ¨
    -0.24
    dings
    -0.24
    KÄ°
    -0.23
    ÂŃtion
    -0.23
    thood
    -0.23
    POSITIVE LOGITS
     trend
    0.26
    asel
    0.26
    ilinear
    0.26
    è¶ĭåĬ¿
    0.26
     paraph
    0.26
    ighbor
    0.26
    uese
    0.25
    osate
    0.25
     cul
    0.24
    é«ĺå°Ķ夫
    0.24
    Activations Density 0.002%

    No Known Activations

    This feature has no known activations.