© 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. 130595
    Prev
    Next
    INDEX
    Explanations

    of

    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
    çĿ¦
    -0.28
     inp
    -0.28
    å®£ä¼łæķĻèĤ²
    -0.25
    èį«
    -0.24
    é¢Ĩ导èĢħ
    -0.24
    inc
    -0.24
    metal
    -0.24
    èĦ©
    -0.23
    plied
    -0.23
    .meta
    -0.23
    POSITIVE LOGITS
    ocha
    0.35
    amat
    0.28
    dia
    0.28
    usal
    0.28
    aidu
    0.26
    tics
    0.26
    æĹłåģ¿
    0.25
    æľĢå¿«çļĦ
    0.25
    stasy
    0.25
     Ãľ
    0.25
    Activations Density 1.072%

    No Known Activations