© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 12-TRANSCODER-HP
    7. 24107
    Prev
    Next
    INDEX
    Explanations

    Numbers and "a"

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    åį°
    -0.25
    å¾ĹæĦı
    -0.25
    icom
    -0.24
    rollers
    -0.24
    å¤ĸæı´
    -0.24
    inker
    -0.23
    å¹³åĿĩ
    -0.23
    ä¼ĺäºİ
    -0.23
    æĺ¯åı¯ä»¥
    -0.23
    .fromString
    -0.23
    POSITIVE LOGITS
    atten
    0.27
    Retention
    0.26
     Ret
    0.25
    etypes
    0.25
    TARGET
    0.25
    _ret
    0.25
    rary
    0.25
     unary
    0.25
    odb
    0.24
     suppl
    0.24
    Activations Density 0.001%

    No Known Activations