© 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. 130044
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    åŀ«
    -0.27
    +]
    -0.26
     backlight
    -0.26
    ITIES
    -0.26
    modelName
    -0.25
    JV
    -0.25
    èĩĤ
    -0.25
     Ones
    -0.25
    çª
    -0.25
    ités
    -0.24
    POSITIVE LOGITS
    éĢ¸
    0.28
    _EOL
    0.27
    èĢĥ
    0.27
    /*!
    0.26
    çļĦ人æĿ¥è¯´
    0.25
    ework
    0.25
    oad
    0.25
    éħįåģ¶
    0.24
    åħ«ä¸ª
    0.24
    èĵĵ
    0.24
    Activations Density 2.961%

    No Known Activations

    This feature has no known activations.