© 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. 22-TRANSCODER-HP
    7. 86985
    Prev
    Next
    INDEX
    Explanations

    Population counts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    acs
    -0.27
    _px
    -0.26
    icorn
    -0.26
     ALS
    -0.25
    rapper
    -0.25
    æģĻ
    -0.25
    vla
    -0.25
    æ¸į
    -0.24
    å¡ŀ
    -0.24
     manual
    -0.23
    POSITIVE LOGITS
     fondo
    0.29
    edd
    0.27
    .eth
    0.27
    _ping
    0.26
     '-',
    0.24
    ROOT
    0.24
    InBackground
    0.24
    éĺ¿æł¹
    0.24
    éģĵå¾·
    0.23
    ä¸įçŁ¥
    0.23
    Activations Density 0.001%

    No Known Activations