© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 23-TRANSCODER-HP
    7. 161838
    Prev
    Next
    INDEX
    Explanations

    shapes and morphologies

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    第ä¸Ģä½į
    -0.28
    ourd
    -0.26
    bed
    -0.26
    çİ°åĩº
    -0.26
    arded
    -0.26
    ecera
    -0.25
    rock
    -0.25
    ä¹ħ
    -0.25
    BED
    -0.24
    inger
    -0.24
    POSITIVE LOGITS
    compound
    0.29
    cly
    0.27
    lemen
    0.26
     eller
    0.25
    EMU
    0.25
    esan
    0.24
    urgeon
    0.23
    骨æŀ¶
    0.23
    -Jul
    0.23
    ubb
    0.23
    Activations Density 0.006%

    No Known Activations