© 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. 88797
    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
     fought
    -0.27
    ij
    -0.25
    spent
    -0.25
     describe
    -0.23
     earned
    -0.23
    interfaces
    -0.23
     moderators
    -0.23
    ÄĻ
    -0.23
    ornings
    -0.23
     effortlessly
    -0.23
    POSITIVE LOGITS
    ogen
    0.27
    ognito
    0.26
    enic
    0.26
    /arch
    0.25
    ÑĤÑĢо
    0.25
    uÃŃ
    0.24
    æĭĸ
    0.24
    çľ¼çļ®
    0.24
    vro
    0.24
    gil
    0.24
    Activations Density 1.403%

    No Known Activations

    This feature has no known activations.