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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 6820
    Prev
    Next
    INDEX
    Explanations

    punctuation, conjunctions

    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
    ष
    -0.30
    宽
    -0.29
    far
    -0.28
     Shield
    -0.28
    onn
    -0.26
     beh
    -0.25
    æĭ¿åĩº
    -0.25
    åIJ¯åıij
    -0.24
    ['__
    -0.24
    onnen
    -0.24
    POSITIVE LOGITS
    å¹´ä¹ĭä¹ħ
    0.29
    ihan
    0.29
    idot
    0.28
     thousand
    0.27
    omat
    0.25
    inger
    0.25
    åħ±äº§
    0.25
    /tasks
    0.25
     comb
    0.24
     ()↵↵
    0.24
    Activations Density 0.028%

    No Known Activations