© 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. 20-TRANSCODER-HP
    7. 129124
    Prev
    Next
    INDEX
    Explanations

    Punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    zej
    -0.28
    oreal
    -0.27
    ony
    -0.26
    æĶ¿æ²»
    -0.25
    oad
    -0.25
    igt
    -0.25
    iet
    -0.25
    orage
    -0.25
     stat
    -0.25
    ibal
    -0.25
    POSITIVE LOGITS
    ROM
    0.28
    æ»ļçIJĥ
    0.27
    quiry
    0.27
     families
    0.25
    åIJĦ家
    0.25
    åĽŀåij³
    0.25
     Bend
    0.24
    åĩłå®¶
    0.24
    okino
    0.24
    ä¸ī家
    0.23
    Activations Density 24.888%

    No Known Activations