© 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. 130372
    Prev
    Next
    INDEX
    Explanations

    Scientific papers

    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
     technicians
    -0.27
     technician
    -0.26
    å©Ĩ
    -0.25
    iams
    -0.24
     managed
    -0.24
     avail
    -0.24
    onaut
    -0.23
    ä¸įåłª
    -0.23
     Technician
    -0.23
     remark
    -0.23
    POSITIVE LOGITS
    ElementException
    0.28
    lexical
    0.24
    [âĢ¦]
    0.24
    çĥĪ士
    0.23
    .setOnClickListener
    0.23
    åIJĪéĩij
    0.23
    è¾Ļ
    0.23
    åĽ«
    0.23
    .Di
    0.23
    åIJİæĤĶ
    0.23
    Activations Density 10.181%

    No Known Activations