© 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. 129903
    Prev
    Next
    INDEX
    Explanations

    Varied informational and descriptive text

    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
    nev
    -0.26
    çĺ¦èº«
    -0.26
    .construct
    -0.25
    rikes
    -0.24
    åºĶ该æĢİä¹Ī
    -0.24
    AdapterManager
    -0.24
     Vy
    -0.24
    __()↵↵
    -0.23
     Against
    -0.23
    让人们
    -0.23
    POSITIVE LOGITS
    iana
    0.28
    leine
    0.27
    enia
    0.27
    aine
    0.26
     thôi
    0.26
    oge
    0.25
    ista
    0.25
    ixin
    0.24
    icia
    0.24
    ienie
    0.24
    Activations Density 14.922%

    No Known Activations