© 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. 90189
    Prev
    Next
    INDEX
    Explanations

    Online shopping, free shipping

    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
     há»ĵng
    -0.28
    ittle
    -0.27
    éĿ´
    -0.26
    ault
    -0.24
    ipse
    -0.24
     flatt
    -0.24
     xhttp
    -0.24
    titulo
    -0.23
     appId
    -0.23
     federation
    -0.23
    POSITIVE LOGITS
     Saunders
    0.30
     eve
    0.28
    çĪ·
    0.27
    çļĦåij½è¿IJ
    0.26
     surprises
    0.25
    (Func
    0.25
     Acting
    0.25
    juries
    0.24
    çĴĥ
    0.24
    _FALL
    0.24
    Activations Density 1.141%

    No Known Activations