© 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. 7640
    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
    åı³æīĭ
    -0.26
     Mellon
    -0.25
     enr
    -0.25
     пÑĢож
    -0.25
     collect
    -0.25
    âĸ»
    -0.25
    å¾ĹçĽĬ
    -0.24
     master
    -0.24
    PELL
    -0.23
    éĻĪåĪĹ
    -0.23
    POSITIVE LOGITS
     ([[
    0.29
    ops
    0.24
    inas
    0.23
    æĥ³åĪ°
    0.23
     Cald
    0.23
    stp
    0.23
     trembling
    0.22
     Athe
    0.22
    orum
    0.22
    (delay
    0.22
    Activations Density 0.714%

    No Known Activations

    This feature has no known activations.