© 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. 89046
    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
    çļĦåħ³æ³¨
    -0.27
     [][]
    -0.24
    &w
    -0.24
    é²ľæĺİ
    -0.24
    IFI
    -0.24
    å¥Ĺ
    -0.24
     [`
    -0.23
     indirect
    -0.23
    enance
    -0.23
    thon
    -0.23
    POSITIVE LOGITS
    æľµ
    0.26
    -mouth
    0.26
    æĬķèµĦé¡¹çĽ®
    0.25
    ControlEvents
    0.25
     adult
    0.23
    unfold
    0.23
     projectile
    0.23
    ori
    0.23
    Displayed
    0.23
    è¾¾ä¸įåĪ°
    0.23
    Activations Density 12.496%

    No Known Activations

    This feature has no known activations.