© 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. 89342
    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
     selection
    -0.28
    ä¸Ĭ线
    -0.27
    abis
    -0.27
     shades
    -0.26
    åĵģç±»
    -0.26
    读书
    -0.25
    éŸ
    -0.25
    gua
    -0.25
     Selection
    -0.25
     départ
    -0.25
    POSITIVE LOGITS
    ä¸ī人
    0.28
    urch
    0.28
    ients
    0.25
    ffc
    0.24
    âĶĬ
    0.24
    à¹Ģลย
    0.24
    entina
    0.24
    .ta
    0.23
     grit
    0.23
    know
    0.23
    Activations Density 2.391%

    No Known Activations

    This feature has no known activations.