© 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. 108045
    Prev
    Next
    INDEX
    Explanations

    contains numbers

    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
    å±
    -0.28
    åĿŀ
    -0.28
    iterated
    -0.26
    æĹ¢èĥ½
    -0.24
    GetSize
    -0.24
    çĿĢéĩį
    -0.24
     homemade
    -0.24
    襦
    -0.24
    dbo
    -0.24
    ISIS
    -0.23
    POSITIVE LOGITS
    logan
    0.28
    å¼łè´´
    0.26
    gan
    0.26
    ados
    0.25
    .linkedin
    0.25
    imeter
    0.24
    genic
    0.24
    -effect
    0.24
     Sm
    0.24
    rowse
    0.24
    Activations Density 9.487%

    No Known Activations