© 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. 149422
    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
    aras
    -0.28
    éĤ´
    -0.25
    ouched
    -0.25
    alking
    -0.25
    ument
    -0.24
    趴
    -0.24
    åľ°ä¸ĭ室
    -0.24
     BaseService
    -0.24
    ĥĿ
    -0.23
    æľĪä¸Ń
    -0.23
    POSITIVE LOGITS
    %%↵
    0.29
     accounts
    0.27
    å¸IJ
    0.26
    è¿Ļæł·çļĦè¯Ŀ
    0.26
    åĬŀæ³ķ
    0.25
     hor
    0.25
     Sc
    0.24
    å®ŀè·µ
    0.24
    è¡Ķ
    0.24
     Accounts
    0.24
    Activations Density 1.439%

    No Known Activations

    This feature has no known activations.