© 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. 4889
    Prev
    Next
    INDEX
    Explanations

    comma

    np_max-act · gemini-2.0-flash
    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
    anel
    -0.27
    åŁĭ
    -0.27
    æħ¨
    -0.26
    belie
    -0.26
    unes
    -0.24
     licensors
    -0.24
    ctrine
    -0.24
    ä»Ĭ天æĪij们
    -0.24
     believers
    -0.23
    ä»ŀ
    -0.23
    POSITIVE LOGITS
    icycle
    0.28
    presso
    0.28
    fr
    0.27
    iction
    0.26
    inox
    0.26
    iclass
    0.26
    (EC
    0.25
    èIJ¼
    0.25
     META
    0.25
     fron
    0.25
    Activations Density 0.210%

    No Known Activations