© 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. 23991
    Prev
    Next
    INDEX
    Explanations

    legal documents

    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
    paired
    -0.28
    athed
    -0.27
    parents
    -0.27
    å¸Ŀ
    -0.26
    ä»ĬæĻļ
    -0.26
     parents
    -0.25
    çĪ¶æ¯į
    -0.25
    opa
    -0.25
     kat
    -0.24
     Rows
    -0.24
    POSITIVE LOGITS
    .addAttribute
    0.26
    PIP
    0.26
    ian
    0.24
    vla
    0.24
    (KP
    0.23
     Mystery
    0.23
    iale
    0.23
    зем
    0.23
    ãĤīãģĦ
    0.23
     Manus
    0.23
    Activations Density 0.017%

    No Known Activations