© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 35-TRANSCODER-HP
    7. 40583
    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
    Negative Logits
     iam
    -0.27
     me
    -0.27
     spine
    -0.25
    åĪĩ
    -0.25
    anan
    -0.24
    é¦Ĭ
    -0.24
     rest
    -0.24
    aina
    -0.24
    ucha
    -0.23
     Cos
    -0.23
    POSITIVE LOGITS
     handleMessage
    0.28
    æ°¸ä¹ħ
    0.28
     originals
    0.25
    té
    0.25
    ENGINE
    0.25
    styl
    0.24
    ẽ
    0.23
    è¿ŀè½½
    0.23
     arbitrarily
    0.23
    gerät
    0.23
    Activations Density 7.582%

    No Known Activations

    This feature has no known activations.