© 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. 20-TRANSCODER-HP
    7. 130322
    Prev
    Next
    INDEX
    Explanations

    Technical writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åĪį
    -0.30
     Schro
    -0.25
    shop
    -0.25
    /commons
    -0.24
    ç¼ķ
    -0.24
    éĽ¾
    -0.23
    第äºĮ个
    -0.23
    ÅĽnie
    -0.23
    bnb
    -0.23
     Means
    -0.23
    POSITIVE LOGITS
    ration
    0.27
     du
    0.26
    %č↵
    0.25
    @test
    0.25
    æ³ķå¸Ī
    0.24
    Reducer
    0.24
    ä½Ľ
    0.24
    ä»ĸåıĪ
    0.23
     Minist
    0.23
     disproportion
    0.23
    Activations Density 83.415%

    No Known Activations