© 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. 89629
    Prev
    Next
    INDEX
    Explanations

    Code/programming

    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
    å®Ī
    -0.27
     whistle
    -0.26
    泪
    -0.25
     interchange
    -0.25
    ÑģÑĤÑĭ
    -0.25
    çģ¯çģ«
    -0.25
     cider
    -0.25
    ^{-
    -0.24
     Assembly
    -0.24
     overs
    -0.24
    POSITIVE LOGITS
     Suspension
    0.25
    æĽ´å¥½çļĦ
    0.25
    æĮĤ
    0.25
    æ··åIJĪ
    0.25
     hybrids
    0.24
    æĮĤåľ¨
    0.24
    itor
    0.24
    جاÙħ
    0.24
    ">-->↵
    0.24
    ä¸Ģèµ·
    0.24
    Activations Density 46.372%

    No Known Activations