© 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. 151173
    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
    rien
    -0.26
    åĮĹ京æŶéĹ´
    -0.26
    eneg
    -0.25
     airs
    -0.24
    _sink
    -0.24
    åłĨ
    -0.24
     blades
    -0.24
     brains
    -0.23
    xBC
    -0.23
     wondered
    -0.23
    POSITIVE LOGITS
     Zub
    0.27
     Dummy
    0.24
    è¶Ĭ
    0.24
     deepest
    0.24
    .root
    0.24
    èī¯
    0.24
     Choice
    0.24
     Necessary
    0.23
    èħ°
    0.23
    æł¹
    0.23
    Activations Density 0.966%

    No Known Activations

    This feature has no known activations.