© 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. 89638
    Prev
    Next
    INDEX
    Explanations

    code/written answers

    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
    涣
    -0.25
    scatter
    -0.25
    -directed
    -0.25
    -hop
    -0.24
    çĥŃæIJľ
    -0.24
    branch
    -0.23
    çe
    -0.23
    enberg
    -0.23
    æĶ¾æīĭ
    -0.23
     directed
    -0.23
    POSITIVE LOGITS
     tun
    0.30
    ,nil
    0.30
    示æĦı
    0.26
     multiplic
    0.26
    èİ«
    0.25
    å¿ħ
    0.24
    suming
    0.24
    =nil
    0.24
    积
    0.24
     lab
    0.24
    Activations Density 6.914%

    No Known Activations