© 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. 40755
    Prev
    Next
    INDEX
    Explanations

    Random text/code

    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
    ncmp
    -0.32
    ="__
    -0.27
    ENCIES
    -0.27
    ç»ŀ
    -0.25
    è¿Ļ件äºĭæĥħ
    -0.25
     pay
    -0.25
     Dexter
    -0.25
     hab
    -0.25
    äºķ
    -0.25
     Prototype
    -0.24
    POSITIVE LOGITS
    uta
    0.26
    ut
    0.26
    -doc
    0.25
    çĺł
    0.24
     Ut
    0.24
     Catalan
    0.24
     contribute
    0.23
    æĸ°éĹ»ä¸Ńå¿ĥ
    0.23
    cz
    0.23
    èµ°äºĨ
    0.23
    Activations Density 0.148%

    No Known Activations