© 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. 7097
    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
    rtle
    -0.28
    åĮ¿åIJį
    -0.28
    ungan
    -0.28
    ello
    -0.27
    EEK
    -0.26
    Ä±ÅŁÄ±
    -0.26
     slicing
    -0.25
    西æ´ĭ
    -0.25
    ellt
    -0.25
    prus
    -0.25
    POSITIVE LOGITS
    对çŃĸ
    0.26
    styled
    0.26
    .less
    0.25
    æĵĴ
    0.25
    lm
    0.24
     Controllers
    0.24
    Replacement
    0.24
    otherwise
    0.24
    èµĦæĸĻ
    0.24
    æĪijå½ĵæŶ
    0.24
    Activations Density 0.077%

    No Known Activations

    This feature has no known activations.