© 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. 89205
    Prev
    Next
    INDEX
    Explanations

    interdisciplinary

    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
    妣
    -0.26
    orce
    -0.25
     heav
    -0.25
    æºIJ头
    -0.25
    .Distance
    -0.24
    entity
    -0.24
    imity
    -0.24
    oring
    -0.24
     suce
    -0.24
     pund
    -0.23
    POSITIVE LOGITS
     missed
    0.28
    çļĦéĹ®é¢ĺ
    0.27
    legg
    0.26
    oose
    0.25
    miss
    0.25
     Nero
    0.24
    æĺ¯å¤ļå°ij
    0.24
    mos
    0.24
     waits
    0.24
    late
    0.24
    Activations Density 20.101%

    No Known Activations