© 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. 62561
    Prev
    Next
    INDEX
    Explanations

    keep

    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
    宾
    -0.30
    çħŀ
    -0.25
    åİ¿åħ¬å®īå±Ģ
    -0.25
    åİ¿
    -0.24
    breaking
    -0.24
    éĻIJ度
    -0.24
    æĩ
    -0.24
    éĢĨ转
    -0.24
    liv
    -0.24
    ductor
    -0.24
    POSITIVE LOGITS
    riba
    0.27
     chords
    0.27
    æĹģ
    0.25
     rif
    0.24
    ascimento
    0.24
    å±ŀäºİ
    0.23
     soar
    0.23
     chord
    0.23
     belongs
    0.23
    å±Ĥ
    0.23
    Activations Density 17.592%

    No Known Activations