© 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. 5050
    Prev
    Next
    INDEX
    Explanations

    programming/technical issues

    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
    ä¾
    -0.28
    ,eg
    -0.27
    зÑĭ
    -0.26
    afil
    -0.25
    formatted
    -0.25
    å¸ģ
    -0.25
     suits
    -0.25
     Goldberg
    -0.24
    waves
    -0.24
    ç«ĻçĿĢ
    -0.24
    POSITIVE LOGITS
    riet
    0.32
    extent
    0.30
     completa
    0.29
     extent
    0.28
    è¶³å¤ŁçļĦ
    0.27
    è¾ĥ大çļĦ
    0.26
     scout
    0.26
    eyond
    0.26
     beyond
    0.26
    æŀģèĩ´
    0.26
    Activations Density 0.004%

    No Known Activations