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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 5702
    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
    ALER
    -0.28
    æĹ®
    -0.27
    olog
    -0.27
    ĵį
    -0.27
    PLY
    -0.26
    /environment
    -0.26
     searching
    -0.24
     ülke
    -0.24
    groupid
    -0.24
    åħ¬åı¸åľ¨
    -0.24
    POSITIVE LOGITS
    /stdc
    0.29
    OMIC
    0.28
    uxt
    0.26
    isci
    0.26
    omic
    0.25
    boro
    0.25
     Hayward
    0.25
     Jefferson
    0.25
    év
    0.24
    istical
    0.24
    Activations Density 2.111%

    No Known Activations

    This feature has no known activations.