© 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. 89132
    Prev
    Next
    INDEX
    Explanations

    Code/Technical content

    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
    æĺİæľĹ
    -0.26
    åłª
    -0.26
     trailing
    -0.26
    vari
    -0.26
    cordova
    -0.26
     way
    -0.25
    å¥Ĺ
    -0.25
    è¶
    -0.24
    /html
    -0.24
    å¾Ħ
    -0.24
    POSITIVE LOGITS
    lut
    0.26
    atars
    0.25
     Lux
    0.25
    .Named
    0.25
    jian
    0.25
    beer
    0.25
    OTES
    0.24
    åįıå®ļ
    0.24
    ae
    0.23
    <unsigned
    0.23
    Activations Density 0.782%

    No Known Activations