© 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. 88362
    Prev
    Next
    INDEX
    Explanations

    articles and prepositions

    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
    pare
    -0.28
     wh
    -0.28
    çģ«çĤ¬
    -0.26
    æĬ¢
    -0.26
    åĢºæĿĥ
    -0.25
    platform
    -0.25
     tribe
    -0.25
    é»Ħéĩij
    -0.25
    s
    -0.24
    ε
    -0.24
    POSITIVE LOGITS
    anova
    0.29
     CONSEQUENTIAL
    0.29
    vé
    0.27
    =value
    0.25
    嵬
    0.25
    DSA
    0.24
    ä»İ容
    0.24
    cce
    0.24
    imoto
    0.24
    æĤ²åĵĢ
    0.24
    Activations Density 13.676%

    No Known Activations