© 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. 63220
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     interp
    -0.30
     frustr
    -0.28
    OLA
    -0.28
    éĻª
    -0.25
    fr
    -0.25
    ORM
    -0.25
    -fontawesome
    -0.24
    rar
    -0.24
    fram
    -0.24
    æĴĴ
    -0.24
    POSITIVE LOGITS
    esimal
    0.32
     mM
    0.28
    kal
    0.26
     Circ
    0.26
    æĬķèµĦé¡¹çĽ®
    0.26
    èµ·éĩį
    0.26
    _DEN
    0.26
    keiten
    0.26
     Passage
    0.26
     hits
    0.25
    Activations Density 17.256%

    No Known Activations

    This feature has no known activations.