© 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. 88610
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    欢
    -0.26
     Fam
    -0.26
    enen
    -0.26
    追寻
    -0.26
    æĹ¶ä»£
    -0.26
    æµģä¼ł
    -0.26
    immer
    -0.25
    åIJ¬
    -0.24
    ä¼łæĿ¥
    -0.24
    cko
    -0.24
    POSITIVE LOGITS
    consin
    0.29
    atomy
    0.29
    odies
    0.28
    gatsby
    0.27
    kie
    0.26
    .GetResponse
    0.26
    ature
    0.25
    erequisite
    0.25
    DTV
    0.25
    rella
    0.24
    Activations Density 1.690%

    No Known Activations

    This feature has no known activations.