© 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. 6507
    Prev
    Next
    INDEX
    Explanations

    just

    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
     grac
    -0.27
    Canon
    -0.24
     Rare
    -0.24
     Sanford
    -0.23
    Rare
    -0.23
    并ä¸İ
    -0.23
    ä¸īä½įä¸Ģä½ĵ
    -0.23
    (arc
    -0.23
    Lint
    -0.23
    amenti
    -0.23
    POSITIVE LOGITS
    istr
    0.34
    ä¸ĢéĿ¢
    0.32
    ä»Ģä¹Īéĥ½
    0.30
    è¿·ä¿¡
    0.27
     PyErr
    0.26
     negative
    0.26
    à¹Ĩ
    0.25
     inconvenient
    0.25
    ãģ¨ãģĦãģĨãģĵãģ¨
    0.25
    ãģ®ãģĵãģ¨
    0.25
    Activations Density 0.026%

    No Known Activations