© 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. 88698
    Prev
    Next
    INDEX
    Explanations

    questions and answers

    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
    è¿ĩ大
    -0.30
     stør
    -0.24
    RR
    -0.24
     radar
    -0.24
    太ä¹ħ
    -0.23
    eneral
    -0.23
    太大
    -0.23
    ạ
    -0.23
     Larger
    -0.23
    é¦ĸéĢī
    -0.23
    POSITIVE LOGITS
    ouro
    0.28
    epar
    0.26
    åĢĴ
    0.26
    ihar
    0.25
    -rights
    0.25
    éĿłçĿĢ
    0.25
    /svg
    0.25
    cycle
    0.24
    ansa
    0.24
    æµıè§Ī
    0.23
    Activations Density 7.960%

    No Known Activations