© 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. 129168
    Prev
    Next
    INDEX
    Explanations

    (x

    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
    l
    -0.30
    roud
    -0.27
    èµĶ
    -0.27
     succeed
    -0.27
    ==$
    -0.26
     Bulk
    -0.26
    京津
    -0.25
    ä¸į失
    -0.25
    aces
    -0.24
     nl
    -0.24
    POSITIVE LOGITS
    éĺı
    0.27
    ç¿»
    0.26
    .flip
    0.26
    evity
    0.26
    éĶī
    0.25
    intern
    0.24
     Lear
    0.24
    庶
    0.24
    ekt
    0.24
    _units
    0.23
    Activations Density 10.384%

    No Known Activations