© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 23-TRANSCODER-HP
    7. 25445
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    dish
    -0.27
    çļĦæĦıè§ģ
    -0.26
     Portfolio
    -0.26
    å±¥
    -0.26
    çļĦå¿ĥæĥħ
    -0.24
    æĹłæķ°æ¬¡
    -0.24
     Solar
    -0.23
    稳å®ļçļĦ
    -0.23
     lights
    -0.23
    Solar
    -0.23
    POSITIVE LOGITS
    åıįèħIJ
    0.28
     oc
    0.25
     plank
    0.25
    èļ°
    0.25
    addock
    0.25
    缩水
    0.25
    çł£
    0.25
    Unmarshaller
    0.24
    nya
    0.24
    ns
    0.23
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.