© 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. 89806
    Prev
    Next
    INDEX
    Explanations

    Period

    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
    hunt
    -0.28
    -Encoding
    -0.27
    æĢİ
    -0.25
    _AD
    -0.25
    æĬ»
    -0.24
    AVA
    -0.24
    outdir
    -0.24
    åĿļæĮģ以
    -0.23
    èĩ¬
    -0.23
    åIJĥäºı
    -0.23
    POSITIVE LOGITS
    amp
    0.25
    çĩ
    0.24
    .wp
    0.24
    [[
    0.24
    ————
    0.23
    thest
    0.23
    缴å±ŀ
    0.23
    rst
    0.23
    uest
    0.23
    pectives
    0.23
    Activations Density 15.459%

    No Known Activations