© 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. 142027
    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
    è¾ĥé«ĺçļĦ
    -0.26
    é£
    -0.26
    åĶĶ
    -0.26
    quent
    -0.25
    åĪĩ
    -0.25
    breaking
    -0.25
    åľ©
    -0.24
    åĪĩãĤĬ
    -0.24
    fmt
    -0.24
     CONTRIBUT
    -0.24
    POSITIVE LOGITS
    CCI
    0.27
     mer
    0.26
     merit
    0.26
    aleigh
    0.25
    SCI
    0.25
    etag
    0.25
    mer
    0.25
    å°ĨæĿ¥
    0.25
    ologically
    0.24
    ä¸Ģæīĭ
    0.24
    Activations Density 36.170%

    No Known Activations

    This feature has no known activations.