© 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. 63129
    Prev
    Next
    INDEX
    Explanations

    to

    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
    Short
    -0.26
     Hort
    -0.25
    short
    -0.25
     Gy
    -0.25
     Guys
    -0.24
     Hobby
    -0.24
    loom
    -0.24
    osome
    -0.23
    éĽī
    -0.23
     useStyles
    -0.23
    POSITIVE LOGITS
     writ
    0.29
     Provid
    0.25
    ä¹Łä¸įè¦ģ
    0.25
    ionale
    0.25
    asts
    0.25
    æıIJä¾ĽæĽ´å¤ļ
    0.25
    afb
    0.24
     Lands
    0.24
    zeigen
    0.24
    _Do
    0.24
    Activations Density 14.141%

    No Known Activations