© 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. 90267
    Prev
    Next
    INDEX
    Explanations

    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
    alom
    -0.27
     campaigns
    -0.26
    umb
    -0.26
    si
    -0.25
    aggio
    -0.25
    artner
    -0.25
    ramer
    -0.25
    æĪIJæľ¬
    -0.25
    xFFFFFF
    -0.24
    UMB
    -0.24
    POSITIVE LOGITS
    outline
    0.30
    trinsic
    0.29
    density
    0.29
     litt
    0.29
    该æĿij
    0.28
    füg
    0.28
    éªĦ
    0.27
     intrinsic
    0.27
    trait
    0.27
    dden
    0.27
    Activations Density 18.515%

    No Known Activations