© 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. 89484
    Prev
    Next
    INDEX
    Explanations

    would/will

    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
    wise
    -0.25
    ble
    -0.25
    æĢİä¹Īä¼ļ
    -0.24
     env
    -0.24
    ilar
    -0.24
     MIS
    -0.24
    -wise
    -0.23
     Blair
    -0.23
    çݯå¢ĥ
    -0.23
    :expr
    -0.23
    POSITIVE LOGITS
    ollo
    0.29
    æĭ¶
    0.29
    inox
    0.27
     breakdown
    0.26
    üp
    0.25
     breaking
    0.24
     breaker
    0.24
    ẻ
    0.24
    åĪ©çĶ¨æĤ¨çļĦ
    0.24
    nees
    0.23
    Activations Density 15.180%

    No Known Activations