© 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. 90325
    Prev
    Next
    INDEX
    Explanations

    Scientific research papers

    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
    Callbacks
    -0.28
    績
    -0.26
    ÑĢÑĥÑģ
    -0.25
    æĬ¥
    -0.24
    Ä°N
    -0.24
    æĬ¥å¤į
    -0.24
    rÃł
    -0.24
    fällt
    -0.24
    =>'
    -0.23
    .lu
    -0.23
    POSITIVE LOGITS
    Pen
    0.27
     Peninsula
    0.26
    ady
    0.26
     Pen
    0.25
     Pew
    0.25
    MO
    0.25
    ocoa
    0.24
    gef
    0.23
     Rescue
    0.23
    eor
    0.23
    Activations Density 23.334%

    No Known Activations