© 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. 18-TRANSCODER-HP
    7. 88125
    Prev
    Next
    INDEX
    Explanations

    Code/Technical documentation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_18.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.18.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    aat
    -0.29
     OVER
    -0.27
     footing
    -0.26
     CORPOR
    -0.26
     CLOCK
    -0.25
    æĤ´
    -0.25
     RULE
    -0.25
    èĺħ
    -0.25
    æ»Ķ
    -0.24
     POR
    -0.24
    POSITIVE LOGITS
    INCT
    0.27
     IRequest
    0.25
    edral
    0.24
    åīįèĢħ
    0.24
     budgets
    0.24
     limp
    0.24
    iani
    0.24
    ibilit
    0.24
     {.
    0.24
    urent
    0.24
    Activations Density 65.749%

    No Known Activations