© 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. 89306
    Prev
    Next
    INDEX
    Explanations

    numbers

    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
    artz
    -0.40
    itz
    -0.28
     reck
    -0.27
    æµ®
    -0.27
    etime
    -0.26
    timeofday
    -0.26
    æµ®åĬ¨
    -0.25
    Ợ
    -0.25
     Cuomo
    -0.25
    į°
    -0.25
    POSITIVE LOGITS
    phis
    0.29
    uhan
    0.28
    Dash
    0.27
     Odin
    0.24
    æ¥Ķ
    0.24
    CL
    0.24
    covers
    0.24
    KT
    0.24
    setFont
    0.24
    eer
    0.23
    Activations Density 19.242%

    No Known Activations