© 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. 24-TRANSCODER-HP
    7. 151128
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_24.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.24.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    (___
    -0.29
    ấn
    -0.26
    uÅŁ
    -0.26
    á»Ļi
    -0.25
    ç»Ĩèħ»
    -0.25
    icter
    -0.25
    usch
    -0.25
    levator
    -0.24
    (props
    -0.24
    å¯Į
    -0.24
    POSITIVE LOGITS
    æĬ½åıĸ
    0.27
    æĬ½
    0.27
    éļĶ离
    0.26
     rec
    0.25
    -rec
    0.24
     batter
    0.24
     translation
    0.24
    æľĹ
    0.24
    rec
    0.24
     strip
    0.24
    Activations Density 0.101%

    No Known Activations

    This feature has no known activations.