© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 20-TRANSCODER-HP
    7. 63020
    Prev
    Next
    INDEX
    Explanations

    Text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    /licenses
    -0.27
    åī¯ä¸»ä»»
    -0.26
     visits
    -0.26
     alignments
    -0.26
     exon
    -0.26
    ippy
    -0.24
    å¾®åŀĭ
    -0.24
     alignment
    -0.24
    _visit
    -0.24
    imon
    -0.24
    POSITIVE LOGITS
    oper
    0.28
    deaux
    0.26
     Dul
    0.25
    æĹłåı¯
    0.25
    質
    0.25
    hil
    0.24
    ä½ľåĩºäºĨ
    0.24
    oton
    0.23
    åĹij
    0.23
    .rem
    0.23
    Activations Density 3.382%

    No Known Activations