© 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. 6430
    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
    łéĻ¤
    -0.30
    abı
    -0.29
    aben
    -0.28
    nen
    -0.26
    idot
    -0.26
    lined
    -0.25
    #line
    -0.25
     lines
    -0.25
    ä¸Ģä¸ĸ
    -0.25
    .splitext
    -0.25
    POSITIVE LOGITS
    åĪijäºĭæ¡Ī件
    0.28
    å«ĸ
    0.27
    bach
    0.26
    lescope
    0.25
    ulls
    0.25
    loud
    0.25
    æīĭæİĮ
    0.24
    razier
    0.24
    _INS
    0.24
    å£°éŁ³
    0.24
    Activations Density 0.045%

    No Known Activations

    This feature has no known activations.