© 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. 31-TRANSCODER-HP
    7. 18080
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_31.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.31.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    appable
    -0.29
    Genres
    -0.26
    SourceType
    -0.26
    åĻ¨æĿIJ
    -0.26
    åķĨä¸ļåĮĸ
    -0.25
    ategorized
    -0.25
    anning
    -0.25
    å®ħ
    -0.24
    vida
    -0.24
     dÃ¼ÅŁÃ¼n
    -0.24
    POSITIVE LOGITS
     spins
    0.28
    åºĹéĩĮ
    0.27
     Ear
    0.27
    raj
    0.26
     spinner
    0.24
     spun
    0.24
    èĻķ
    0.24
     referee
    0.24
    si
    0.23
    çĽij管éĥ¨éŨ
    0.23
    Activations Density 0.129%

    No Known Activations

    This feature has no known activations.