© 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. 7623
    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
    ATERIAL
    -0.31
     realizing
    -0.27
    åľ°ä¸Ń
    -0.27
     trá»Ŀi
    -0.26
    .fits
    -0.25
    aret
    -0.25
     realize
    -0.25
    äºĴ缸
    -0.24
     fle
    -0.24
     Arbitrary
    -0.23
    POSITIVE LOGITS
    eping
    0.28
     slur
    0.26
    łģ
    0.25
    aday
    0.25
    ç¥ľ
    0.25
    ünd
    0.24
    çĸı
    0.24
    é»į
    0.24
     unic
    0.24
    зон
    0.24
    Activations Density 0.005%

    No Known Activations

    This feature has no known activations.