© 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. 90335
    Prev
    Next
    INDEX
    Explanations

    numbers and calculations

    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
    è´¡çĮ®
    -0.41
     contributing
    -0.40
     contribution
    -0.38
     contributions
    -0.38
    èĥ½èĢĹ
    -0.36
     contributors
    -0.34
     energy
    -0.33
     sum
    -0.33
    contrib
    -0.32
     multiplied
    -0.32
    POSITIVE LOGITS
    BorderColor
    0.26
    olist
    0.25
    èĢ³
    0.25
    nice
    0.24
    helm
    0.23
    縱
    0.23
    виз
    0.23
    溺
    0.23
    对ä»ĺ
    0.23
    rw
    0.23
    Activations Density 16.465%

    No Known Activations