© 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. 14-TRANSCODER-HP
    7. 40773
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_14.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.14.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uite
    -0.29
    лин
    -0.28
    imas
    -0.27
     poems
    -0.26
    igrams
    -0.26
    inis
    -0.26
    è¿ħ
    -0.25
    arris
    -0.25
    emic
    -0.24
    .setItems
    -0.24
    POSITIVE LOGITS
    gew
    0.30
    uto
    0.28
    ech
    0.26
    æ·¡æ°´
    0.24
     Tel
    0.24
    èĥľè´Ł
    0.24
     pragma
    0.24
    itch
    0.24
    [".
    0.24
    [ch
    0.23
    Activations Density 1.633%

    No Known Activations

    This feature has no known activations.