© 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. 88554
    Prev
    Next
    INDEX
    Explanations

    with

    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
    交
    -0.28
     Pai
    -0.27
    ance
    -0.27
     Rolls
    -0.26
    i
    -0.26
    ab
    -0.25
    æĥ³åĪ°
    -0.25
     Lig
    -0.25
     gasoline
    -0.25
    åĦ¡
    -0.25
    POSITIVE LOGITS
    quirer
    0.28
    elle
    0.26
    ottie
    0.25
    /stretch
    0.25
    immutable
    0.25
    Thêm
    0.25
    =num
    0.24
    æĽ²
    0.24
    .fits
    0.24
    otch
    0.24
    Activations Density 8.704%

    No Known Activations