© 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. 89411
    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
     deposit
    -0.26
    ложениÑı
    -0.25
     Yates
    -0.25
     intimate
    -0.24
    <th
    -0.24
    ç»ĨåĪĻ
    -0.24
    avan
    -0.24
     ax
    -0.24
     ultr
    -0.23
     Controls
    -0.23
    POSITIVE LOGITS
    anka
    0.26
    urga
    0.26
    ño
    0.25
    atron
    0.25
     patented
    0.24
    ira
    0.24
    ->[
    0.24
     yaÅŁayan
    0.24
    祯
    0.24
    iran
    0.24
    Activations Density 1.637%

    No Known Activations

    This feature has no known activations.