© 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. 22038
    Prev
    Next
    INDEX
    Explanations

    Extracted website/research snippets

    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
     interstate
    -0.27
     Edition
    -0.26
    åĩĿ
    -0.25
    ivate
    -0.24
    -blocking
    -0.24
    #{@
    -0.24
    é«ĺåľ°
    -0.23
    ×ķ׾×Ķ
    -0.23
    追究
    -0.23
    iggins
    -0.23
    POSITIVE LOGITS
    é¢ł
    0.28
    åīĮ
    0.27
    Cars
    0.27
    å¾Ī满æĦı
    0.25
    callbacks
    0.25
    å¥Ķè·ij
    0.24
    à¤
    0.24
    çĨ
    0.24
    Callback
    0.23
    Servers
    0.23
    Activations Density 0.000%

    No Known Activations