© 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. 141188
    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
    dden
    -0.29
    åħ³éĶ®æĬĢæľ¯
    -0.28
    æı¡
    -0.28
    çłĶ究
    -0.27
    bron
    -0.26
    ä½łæĢİä¹Ī
    -0.25
    åĽ½å®¶çº§
    -0.25
    lie
    -0.25
    è°®
    -0.24
    ays
    -0.24
    POSITIVE LOGITS
    æ°ij主çĶŁæ´»
    0.28
    æ©Ľ
    0.28
    ||
    0.27
    oin
    0.25
    -efficient
    0.25
    /unit
    0.24
    .collections
    0.24
    çī¹åĪ«å£°æĺİ
    0.24
    _BT
    0.24
     slice
    0.23
    Activations Density 0.008%

    No Known Activations

    This feature has no known activations.