© 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. 31-TRANSCODER-HP
    7. 18958
    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
     containers
    -0.26
    ="#"><
    -0.25
    饫
    -0.25
    anner
    -0.25
     quieter
    -0.24
     triangular
    -0.24
    ãģ£ãģ½
    -0.24
     pozostaÅĤ
    -0.23
    çŀ§
    -0.23
    Container
    -0.23
    POSITIVE LOGITS
    ãĥ§ãĥ³
    0.29
    è·Ľ
    0.27
    eil
    0.25
    麸
    0.25
    å·¥åķĨå±Ģ
    0.25
    wyn
    0.24
     cljs
    0.24
    /swagger
    0.24
    失è°ĥ
    0.24
    -interface
    0.23
    Activations Density 0.050%

    No Known Activations

    This feature has no known activations.