© 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. 31-TRANSCODER-HP
    7. 19662
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_31.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.31.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æIJª
    -0.25
    太å°ij
    -0.25
    loo
    -0.25
     mime
    -0.25
    ãĤĴå¾Ĺ
    -0.23
     POP
    -0.23
    æĬĢæľ¯æĶ¯æĮģ
    -0.23
     lug
    -0.23
     ör
    -0.23
     depart
    -0.23
    POSITIVE LOGITS
    addComponent
    0.29
    andal
    0.27
    å¹²æ¶ī
    0.25
    åĪĨåĪ«æĺ¯
    0.25
    å¹²äºĭ
    0.25
    æĪIJé¾Ļ
    0.24
    _COMPONENT
    0.24
    æĮĩ
    0.24
    iceps
    0.24
    agas
    0.24
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.