© 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. 89261
    Prev
    Next
    INDEX
    Explanations

    code, programming

    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
    clus
    -0.28
    ingles
    -0.27
    åı£æľį
    -0.26
    steller
    -0.26
     (::
    -0.25
    æĿ¡è¯Ħ论
    -0.24
    )::
    -0.24
    éĤķ
    -0.24
    getModel
    -0.24
     ::↵
    -0.24
    POSITIVE LOGITS
    plash
    0.28
    hpp
    0.28
    shaft
    0.28
     laz
    0.26
    heads
    0.25
    å¸Ĥåľºä»·æł¼
    0.25
    è¦ģçĤ¹
    0.25
    oras
    0.24
     Trad
    0.24
    ãĥĥãĤ·ãĥ¥
    0.24
    Activations Density 2.157%

    No Known Activations