© 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. 7811
    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
    åħ±éĿĴ
    -0.31
     SECRET
    -0.29
    SECRET
    -0.29
     stale
    -0.27
    .endswith
    -0.26
    çĢĽ
    -0.26
    å°ıåºĹ
    -0.25
    åĩºåħ¥å¢ĥ
    -0.25
     STRICT
    -0.25
    Secret
    -0.25
    POSITIVE LOGITS
    assi
    0.28
    ced
    0.28
     integrated
    0.26
    INI
    0.26
    ug
    0.26
    æĮĤ
    0.25
    æĹģ
    0.25
     incompatible
    0.25
    é¦Ļ
    0.25
    ASS
    0.25
    Activations Density 0.498%

    No Known Activations

    This feature has no known activations.