© 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. 130684
    Prev
    Next
    INDEX
    Explanations

    General text

    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
    иÑĢовка
    -0.29
     drains
    -0.29
    vere
    -0.28
    icated
    -0.26
     Drain
    -0.26
    icer
    -0.25
    âĸ·
    -0.25
    ypi
    -0.25
    iced
    -0.25
    è¿ģ移
    -0.24
    POSITIVE LOGITS
     unlike
    0.29
     full
    0.28
    åħ¨
    0.28
     rẻ
    0.27
    orse
    0.26
     clean
    0.26
    ÃŃ
    0.26
    åħ¨è¿ĩç¨ĭ
    0.26
     like
    0.26
    lı
    0.26
    Activations Density 14.183%

    No Known Activations