© 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. 62685
    Prev
    Next
    INDEX
    Explanations

    software and technical content

    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
    pherical
    -0.29
    cum
    -0.28
    hu
    -0.28
    la
    -0.27
    çıĻ
    -0.25
     getBy
    -0.25
     chance
    -0.25
    ä¹IJè§Ĥ
    -0.24
    utm
    -0.24
    stellung
    -0.24
    POSITIVE LOGITS
     selber
    0.25
    Ñģов
    0.25
    Cpp
    0.25
    inati
    0.25
     themselves
    0.24
     yourselves
    0.24
     remind
    0.24
    achten
    0.24
    _own
    0.24
    ees
    0.24
    Activations Density 6.790%

    No Known Activations