© 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. 100
    Prev
    Next
    INDEX
    Explanations

    code, mode

    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
    ystone
    -0.26
    vester
    -0.26
    çĶŁ
    -0.25
    ضÙħ
    -0.25
    cents
    -0.25
    rians
    -0.25
    åĨ²
    -0.24
    arez
    -0.24
    çĸ«
    -0.24
    é£İåIJ¹
    -0.24
    POSITIVE LOGITS
    éĢĴ
    0.26
    aha
    0.26
     GLsizei
    0.25
    aten
    0.25
    éģŀ
    0.24
     modulo
    0.24
    éĹ´
    0.23
    DEM
    0.23
    ieu
    0.23
    客æĪ¿
    0.23
    Activations Density 0.507%

    No Known Activations