© 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. 140566
    Prev
    Next
    INDEX
    Explanations

    technical documents

    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
     whichever
    -0.26
     whatever
    -0.26
     nothing
    -0.25
    ampler
    -0.25
    ä¸ŃéĢĶ
    -0.24
    ä¸įè¿ĩæĺ¯
    -0.24
    empty
    -0.24
    ä»ĭ
    -0.24
     settlement
    -0.23
     quoi
    -0.23
    POSITIVE LOGITS
     Canter
    0.30
    resents
    0.28
    çļĤ
    0.27
    asma
    0.26
    atial
    0.26
     sustain
    0.26
     sortie
    0.25
    zeigt
    0.24
    ocio
    0.24
    伸ãģ³
    0.24
    Activations Density 2.768%

    No Known Activations