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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 6067
    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
    çIJĩ
    -0.27
    åľ¨è¿Ļç§į
    -0.26
    cff
    -0.26
    å¾Ī大ç¨ĭ度
    -0.25
    è¿Ŀ纪
    -0.24
     Cous
    -0.24
     reused
    -0.24
    POINT
    -0.24
    аниз
    -0.24
    侧
    -0.24
    POSITIVE LOGITS
    è°¦
    0.29
     Listing
    0.25
    acam
    0.25
     sung
    0.24
     Rams
    0.24
    icare
    0.24
    çªģçĦ¶
    0.23
     indef
    0.23
    ereum
    0.23
    (actual
    0.23
    Activations Density 0.026%

    No Known Activations

    This feature has no known activations.