© 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. 33-TRANSCODER-HP
    7. 53210
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    isor
    -0.24
    DVD
    -0.24
    pio
    -0.24
    rvine
    -0.24
    adt
    -0.24
    -night
    -0.24
    ''↵
    -0.24
    {-
    -0.23
    hole
    -0.23
     subsidi
    -0.23
    POSITIVE LOGITS
    æŁIJç§įç¨ĭ度
    0.30
    æĽ´å¥½çļĦ
    0.27
    ulence
    0.26
    Blo
    0.26
    zy
    0.26
    leans
    0.26
    ums
    0.26
    ous
    0.26
    æĹºåŃ£
    0.26
    .zh
    0.26
    Activations Density 0.001%

    No Known Activations

    This feature has no known activations.