© 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. 4-TRANSCODER-HP
    7. 166
    Prev
    Next
    INDEX
    Explanations

    computing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_4.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.4.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    otos
    -0.28
    agram
    -0.28
     comb
    -0.27
    ĶåĽŀ
    -0.26
    PointerType
    -0.26
    null
    -0.25
     Charter
    -0.25
    oto
    -0.25
     Northern
    -0.25
    odes
    -0.25
    POSITIVE LOGITS
     mour
    0.27
     THR
    0.26
    uÃŃ
    0.26
     culturally
    0.25
    aldo
    0.24
    woke
    0.24
    sink
    0.24
     midterm
    0.24
    relu
    0.24
     Aralık
    0.24
    Activations Density 3.852%

    No Known Activations