© 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. 89209
    Prev
    Next
    INDEX
    Explanations

    technical/code contexts

    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
    åĢŁ
    -0.30
    æģĴ
    -0.28
     mô
    -0.24
    è´¹
    -0.23
    Scheduled
    -0.23
     jo
    -0.23
    .Globalization
    -0.23
    çķ¥
    -0.23
     availability
    -0.23
     Fixed
    -0.23
    POSITIVE LOGITS
    irst
    0.34
    çļĦéĤ£ç§į
    0.27
    ãĤ¿ãĥ«
    0.26
    IRST
    0.26
     PERF
    0.26
    ACES
    0.26
    _apps
    0.26
    rias
    0.25
     disastr
    0.25
    igy
    0.25
    Activations Density 0.908%

    No Known Activations