© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 20-TRANSCODER-HP
    7. 63527
    Prev
    Next
    INDEX
    Explanations

    solar

    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
    Not in Any Lists

    No Comments

    Negative Logits
     CONTRIBUTORS
    -0.29
    ars
    -0.26
     improv
    -0.26
    举
    -0.26
    åĨį
    -0.26
    仨
    -0.24
    ARS
    -0.24
    estr
    -0.24
    _COUNTER
    -0.24
     Zy
    -0.24
    POSITIVE LOGITS
    é»ij马
    0.27
    åħ®
    0.24
    ::$_
    0.24
     ration
    0.24
    !(:
    0.24
    å¼Ģåĩº
    0.23
    Rank
    0.23
    reservation
    0.23
     rank
    0.23
     $#
    0.23
    Activations Density 6.249%

    No Known Activations