© 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. 88502
    Prev
    Next
    INDEX
    Explanations

    's

    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
    ç»ĦæĪIJ
    -0.26
    oplay
    -0.26
    sWith
    -0.26
    SEX
    -0.25
     Ung
    -0.25
    书éĿ¢
    -0.25
    åı£ä¸Ń
    -0.25
    YTE
    -0.25
     Tel
    -0.24
    游ä¹IJ
    -0.24
    POSITIVE LOGITS
    antine
    0.30
    ellan
    0.26
    ä»Ģ
    0.26
     rever
    0.25
    âĮ«
    0.24
     getInfo
    0.24
    pread
    0.23
    otland
    0.23
     simply
    0.23
    ä¸įåģļ
    0.23
    Activations Density 2.704%

    No Known Activations