© 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. 89225
    Prev
    Next
    INDEX
    Explanations

    narrative snippets

    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
    è²łãģij
    -0.25
    shr
    -0.25
    æİĮ声
    -0.25
    ç¢Ľ
    -0.25
    unable
    -0.24
    ạc
    -0.24
    extras
    -0.24
    anko
    -0.24
     Converted
    -0.23
    æĮ£æīİ
    -0.23
    POSITIVE LOGITS
    åŃ³
    0.30
    ESIS
    0.28
    çļĦæĬķèµĦ
    0.27
    etic
    0.27
     cáºŃn
    0.26
    tz
    0.26
    æ£Ģ
    0.25
    æł¼
    0.25
    æ£ĢéªĮ
    0.25
    梯éĺŁ
    0.25
    Activations Density 44.955%

    No Known Activations