© 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. 149259
    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
    Negative Logits
    omi
    -0.25
    enn
    -0.24
    MASK
    -0.24
    iao
    -0.24
    ÅĽni
    -0.24
    å¯Ħæīĺ
    -0.23
    没åħ³ç³»
    -0.23
    èģªæĺİ
    -0.23
    çģ¶
    -0.23
    éħįæĸ¹
    -0.23
    POSITIVE LOGITS
    alom
    0.31
    izzly
    0.30
     Holl
    0.28
    affe
    0.27
    essions
    0.27
    shal
    0.26
     boots
    0.25
    纵åIJij
    0.25
    纵
    0.25
     intentional
    0.25
    Activations Density 0.113%

    No Known Activations

    This feature has no known activations.