© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 18-TRANSCODER-HP
    7. 89428
    Prev
    Next
    INDEX
    Explanations

    scraped data

    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
    Not in Any Lists

    No Comments

    Negative Logits
     Ear
    -0.29
    çļĦæĶ¯æĮģ
    -0.27
    vement
    -0.26
    åĬĽè¿ĺæĺ¯
    -0.26
    Numeric
    -0.25
    è¡Ĺä¸Ĭ
    -0.25
    èĢ³
    -0.25
    åħ¨éĿ¢æİ¨è¿Ľ
    -0.25
    çĨŁ
    -0.24
    æ©Ħæ¦Ħ
    -0.24
    POSITIVE LOGITS
    filer
    0.28
     Wyatt
    0.27
    æľīä»·åĢ¼çļĦ
    0.27
    wy
    0.26
    为éĩįçĤ¹
    0.26
     Revel
    0.26
    æľīä»·åĢ¼
    0.26
    .DialogResult
    0.25
    uyo
    0.25
    é£Łæ¬²
    0.24
    Activations Density 14.188%

    No Known Activations