© 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. 40103
    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
     tools
    -0.32
    å·¥åħ·
    -0.32
    åħ¹
    -0.29
     chá»ĵng
    -0.28
    enko
    -0.28
    tools
    -0.27
    loor
    -0.26
    owan
    -0.26
    à¸ĺร
    -0.26
    owitz
    -0.26
    POSITIVE LOGITS
    .cms
    0.28
    夺åıĸ
    0.28
     Unity
    0.24
    æĪijçľĭ
    0.24
     hybrids
    0.24
    夺
    0.24
    /native
    0.24
    burg
    0.24
    å°¼æĸ¯
    0.24
     hybrid
    0.23
    Activations Density 1.429%

    No Known Activations

    This feature has no known activations.