© 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. 25-TRANSCODER-HP
    7. 107020
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    çijĽ
    -0.30
    åĬłéĩį
    -0.27
     Bri
    -0.27
    çıį
    -0.24
     arm
    -0.24
    rior
    -0.23
    riority
    -0.23
     shattered
    -0.23
    izer
    -0.23
    tam
    -0.23
    POSITIVE LOGITS
    _MUT
    0.32
     Mut
    0.28
    ä¸Ńåħ³
    0.28
    ç¼Ł
    0.27
    adow
    0.26
    ç§į
    0.26
    pan
    0.25
    lops
    0.25
     ÑĢеÑĪил
    0.24
    æµ·è¾¹
    0.24
    Activations Density 0.023%

    No Known Activations

    This feature has no known activations.