© 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. 21923
    Prev
    Next
    INDEX
    Explanations

    joint/joints

    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
    enn
    -0.26
    uche
    -0.26
     Brigham
    -0.25
    odoxy
    -0.24
    alty
    -0.24
    iture
    -0.24
    骨
    -0.24
    éĺ³åİ¿
    -0.24
     roots
    -0.24
    ä¸Ģåij³
    -0.23
    POSITIVE LOGITS
    请çĤ¹åĩ»
    0.30
    碰
    0.30
    click
    0.27
    nett
    0.26
    .hm
    0.25
     click
    0.25
     leak
    0.25
    缺åı£
    0.25
     spot
    0.25
    (click
    0.25
    Activations Density 0.010%

    No Known Activations