© 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. 14-TRANSCODER-HP
    7. 40765
    Prev
    Next
    INDEX
    Explanations

    Code and unusual characters

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_14.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.14.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åĨ¶
    -0.32
    ·»
    -0.29
     rij
    -0.26
    æĪijçľĭ
    -0.26
    樵
    -0.24
    å¤ľæĻļ
    -0.24
    æĭ´
    -0.24
    æĻļä¸Ĭ
    -0.24
    ä¸¤å¼ł
    -0.24
     wanna
    -0.24
    POSITIVE LOGITS
    åıĸèĥľ
    0.26
     merits
    0.24
    _EOL
    0.24
    羦
    0.24
    æµ®åĬ¨
    0.24
    utable
    0.24
    éĩijåŃĹå¡Ķ
    0.24
    {text
    0.24
     campaign
    0.23
    ocos
    0.23
    Activations Density 0.053%

    No Known Activations