© 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. 88673
    Prev
    Next
    INDEX
    Explanations

    2

    np_max-act · gemini-2.0-flash
    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
     covered
    -0.25
    æıŃ
    -0.24
     Âł Âł
    -0.24
     coverage
    -0.24
    irut
    -0.24
    ulate
    -0.24
     peeled
    -0.24
    åŃĶéĽĢ
    -0.24
    uled
    -0.23
    ä¹ĭä¸ĭ
    -0.23
    POSITIVE LOGITS
     maxim
    0.31
    æľīæķĪçļĦ
    0.31
    æľĢ大éĻIJ度
    0.30
     reliably
    0.30
     efficiently
    0.29
    ç¡®ä¿Ŀ
    0.29
    æľīæķĪåľ°
    0.28
    æľĢ大åĮĸ
    0.28
    èī¯
    0.28
     plat
    0.28
    Activations Density 88.248%

    No Known Activations