© 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. 88948
    Prev
    Next
    INDEX
    Explanations

    Computer programming and games

    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
    æµĵ度
    -0.29
    éal
    -0.28
    emade
    -0.28
    adol
    -0.27
    rypto
    -0.26
    ewear
    -0.26
    oplan
    -0.26
    æĺŁçº§éħĴåºĹ
    -0.26
    è§Ĵèī²
    -0.25
    riad
    -0.25
    POSITIVE LOGITS
     IT
    0.33
    IT
    0.32
    ↵↵
    0.29
     hinge
    0.28
    ãĤī
    0.27
    wise
    0.26
    UI
    0.25
    Ui
    0.25
    Err
    0.25
     ITS
    0.25
    Activations Density 7.558%

    No Known Activations