© 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. 149219
    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
    æ´ĭ
    -0.31
    å®ŀè·µç»ıéªĮ
    -0.26
    choices
    -0.26
    Choice
    -0.25
    runtime
    -0.25
    upp
    -0.25
    achten
    -0.25
    choice
    -0.24
     acomp
    -0.24
    -choice
    -0.24
    POSITIVE LOGITS
    лÑģÑı
    0.27
    aille
    0.25
    leck
    0.25
     pres
    0.25
     bench
    0.24
     Lac
    0.24
    常å·ŀ
    0.24
    yleft
    0.24
    OVE
    0.24
    ÃŃm
    0.24
    Activations Density 0.496%

    No Known Activations

    This feature has no known activations.