© 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. 35-TRANSCODER-HP
    7. 39182
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_35.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.35.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ataires
    -0.24
     synth
    -0.24
     \"{
    -0.24
     nonetheless
    -0.24
     stringstream
    -0.23
     categoryName
    -0.23
     Atat
    -0.23
    -stack
    -0.23
    ä¼ĹæīĢ
    -0.23
    ç§ĺ书éķ¿
    -0.23
    POSITIVE LOGITS
     (
    0.29
    ↵↵
    0.28
     _
    0.28
     å
    0.28
     Internal
    0.28
     åħ
    0.27
    å°±
    0.27
     “
    0.27
     åı
    0.27
    0.27
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.