© 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. 54409
    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
    IDX
    -0.26
    /container
    -0.26
    undry
    -0.26
    å¢ŀéķ¿
    -0.26
     <--
    -0.25
    --,
    -0.25
     DESIGN
    -0.24
    ±Ð¾ÑĤ
    -0.24
     Always
    -0.23
    .shtml
    -0.23
    POSITIVE LOGITS
    èĪī
    0.25
    èµĦæĸĻæĺ¾ç¤º
    0.24
    ymph
    0.24
    纸质
    0.24
    ordination
    0.24
    让èĩªå·±
    0.24
    tá
    0.23
    åij¼åIJ¸
    0.23
    åħ¨åĽ½
    0.23
    ilarity
    0.23
    Activations Density 0.003%

    No Known Activations

    This feature has no known activations.