© 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. 53402
    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
     intent
    -0.27
    è
    -0.26
    é¦ĸåıij
    -0.26
    yz
    -0.25
     rear
    -0.25
    po
    -0.25
    rew
    -0.24
     quar
    -0.24
     yuk
    -0.24
    ç®ĹäºĨ
    -0.24
    POSITIVE LOGITS
    ObjectName
    0.25
    åĽ¾å½¢
    0.25
    è§ĦèĮĥåĮĸ
    0.25
    лÑĮн
    0.25
    Tail
    0.24
    IRM
    0.24
    Kn
    0.24
    个åĪ«
    0.24
    afia
    0.23
    Wheel
    0.23
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.