© 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. 19640
    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
    åŃĺè´§
    -0.32
    没æľīåĬŀæ³ķ
    -0.27
    責任
    -0.25
    -through
    -0.25
     Durch
    -0.25
    through
    -0.24
    å²Ń
    -0.24
     Gate
    -0.24
    ense
    -0.24
     hindsight
    -0.24
    POSITIVE LOGITS
     attracting
    0.29
    iro
    0.28
    åĬĽåѦ
    0.28
    ermann
    0.27
    onders
    0.27
    essler
    0.27
    emacs
    0.27
    éĴİ
    0.26
     Serializable
    0.26
    æİĴè¡Įæ¦ľ
    0.26
    Activations Density 12.858%

    No Known Activations

    This feature has no known activations.