© 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. 7605
    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
    æħĮ
    -0.30
    (MAX
    -0.27
    åºı
    -0.25
    (ConfigurationManager
    -0.25
    æ´ª
    -0.24
    èįīåľ°
    -0.23
    éģ¿
    -0.23
    èįī
    -0.23
    .—
    -0.23
    there
    -0.23
    POSITIVE LOGITS
    otron
    0.26
    strip
    0.25
     ########################################################################
    0.25
    .strip
    0.25
     vis
    0.25
    åĴĿ
    0.24
    .hasNext
    0.24
    ä¹Łæ¯Ķè¾ĥ
    0.24
     strips
    0.24
    _attached
    0.24
    Activations Density 1.073%

    No Known Activations

    This feature has no known activations.