© 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. 63878
    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
    estone
    -0.28
    ions
    -0.26
    igos
    -0.26
    estre
    -0.26
    utors
    -0.26
    ObjectType
    -0.25
    tees
    -0.24
     less
    -0.24
    avian
    -0.24
     lag
    -0.24
    POSITIVE LOGITS
    regexp
    0.27
    orp
    0.26
     Offer
    0.24
    åĪ¶æľį
    0.24
    desk
    0.23
    ãĤ³ãĥ¼
    0.23
    åIJ¸å¼ķæĽ´å¤ļ
    0.23
    eryl
    0.23
    åŁ
    0.23
    ί
    0.23
    Activations Density 13.286%

    No Known Activations

    This feature has no known activations.