© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Qwen3-4B
    3. 19-TRANSCODER-HP
    4. 5166
    Prev
    Next
    INDEX
    Explanations

    Technical discussions and text

    np_max-act · gemini-2.0-flash
    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
    nees
    -0.29
     robber
    -0.25
    erts
    -0.25
    á»ĥn
    -0.24
    æĬ¤åį«
    -0.24
    åįģåĪĨéĴŁ
    -0.23
    çķĻä½ı
    -0.23
    ìľ¡
    -0.23
     wrappers
    -0.23
    cho
    -0.23
    POSITIVE LOGITS
    容
    0.30
    éĻIJãĤĬ
    0.27
    zug
    0.26
    iegel
    0.26
     zw
    0.25
    baum
    0.24
    ieu
    0.24
    表
    0.24
    çĽĸ
    0.23
    è¿Ľ
    0.23
    Activations Density 4.448%

    No Known Activations