© 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. 39440
    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
    贯彻
    -0.26
    č↵↵
    -0.25
    åµĮ
    -0.24
    ÙĤØ·
    -0.24
    å±ħ
    -0.24
     corrid
    -0.24
    æĢ»å±Ģ
    -0.24
    rica
    -0.23
    ä¸ĢåĪ»
    -0.23
    la
    -0.23
    POSITIVE LOGITS
    apr
    0.27
     hands
    0.27
     sediment
    0.27
    å¨ij
    0.25
    ILT
    0.23
    åħļç»Ħç»ĩ
    0.23
    _ff
    0.23
    -life
    0.23
     humidity
    0.23
    åĥı个
    0.23
    Activations Density 13.439%

    No Known Activations

    This feature has no known activations.