© 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. 7072
    Prev
    Next
    INDEX
    Explanations

    Questions

    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
    arov
    -0.34
    éĺ³
    -0.28
    åīįæīĢ
    -0.26
    æĪIJè´¥
    -0.26
    常çĶ¨
    -0.25
    éĺ´
    -0.25
    åı¯æĥ³èĢĮçŁ¥
    -0.25
    é
    -0.25
    æĶ¾æīĭ
    -0.24
    uron
    -0.24
    POSITIVE LOGITS
    人åĿĩ
    0.35
    .gms
    0.27
    ESH
    0.26
     QT
    0.26
     ETA
    0.26
    VRT
    0.26
    pcf
    0.25
    ãĢĤwww
    0.24
    .Q
    0.24
    uled
    0.24
    Activations Density 0.006%

    No Known Activations