© 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. 41343
    Prev
    Next
    INDEX
    Explanations

    scientific names

    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
    ida
    -0.27
     wzglÄĻd
    -0.27
    amer
    -0.26
     xamarin
    -0.25
    ider
    -0.24
     Needle
    -0.24
    ид
    -0.24
    ç¼Ĺ
    -0.24
     transcript
    -0.24
    æĺ¯ä»¥
    -0.24
    POSITIVE LOGITS
    chia
    0.32
    åIJĮæĻĤãģ«
    0.28
    èĴĻ
    0.27
    ä¹ŁçŁ¥éģĵ
    0.27
    ä¸Ģéĥ¨
    0.25
    link
    0.25
    ä¸ĢæĬ¹
    0.24
    Vals
    0.24
    vent
    0.24
     Trouble
    0.24
    Activations Density 0.695%

    No Known Activations