© 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. 41030
    Prev
    Next
    INDEX
    Explanations

    Dates and locations

    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
    çľģéĴ±
    -0.29
    linear
    -0.28
    ä¼łçľŁ
    -0.27
    hotmail
    -0.26
    èĢĮåİ»
    -0.26
    çŃ¹èµĦ
    -0.25
     Buildings
    -0.25
     Bethlehem
    -0.24
    cis
    -0.24
    lon
    -0.24
    POSITIVE LOGITS
    æĬ¹
    0.27
    гал
    0.25
     aud
    0.25
    _scr
    0.25
    çļĦæľīæķĪ
    0.24
    çĽĨ
    0.24
     plum
    0.24
    ä½ľæĸĩ
    0.24
    åľ¨åĵª
    0.24
    arks
    0.23
    Activations Density 0.352%

    No Known Activations