© 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. 8921
    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
    SYM
    -0.31
    å¸ĥ
    -0.27
    uble
    -0.25
    éĽĨåĽ¢
    -0.25
    gin
    -0.24
    .android
    -0.24
    éĽĨåľĺ
    -0.24
    åıĮåıĮ
    -0.24
    ç»Ħ
    -0.23
    oyer
    -0.23
    POSITIVE LOGITS
    çĨı
    0.29
    ä½Ĩ她
    0.27
    kdir
    0.27
    perature
    0.27
    ritis
    0.26
    Plug
    0.25
    peg
    0.24
    容纳
    0.24
    åıŃ
    0.24
    èĨĽ
    0.23
    Activations Density 3.188%

    No Known Activations

    This feature has no known activations.