© 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. 21996
    Prev
    Next
    INDEX
    Explanations

    measurement, marking

    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
    å®ļä½į
    -0.27
     Spicer
    -0.26
    innen
    -0.24
     vegas
    -0.24
     civilization
    -0.24
    èŃĺ
    -0.23
    stile
    -0.23
    eses
    -0.23
    ovie
    -0.23
    dbname
    -0.23
    POSITIVE LOGITS
    æĦı大
    0.31
     sentiment
    0.29
    conj
    0.27
    keit
    0.26
     rev
    0.25
     v
    0.25
     nod
    0.25
    ilot
    0.24
    æľĢéķ¿
    0.24
    mic
    0.24
    Activations Density 0.000%

    No Known Activations