© 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. 130265
    Prev
    Next
    INDEX
    Explanations

    Code/References/Links

    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
     reap
    -0.28
    çªģ
    -0.26
     Hour
    -0.26
    straction
    -0.25
    åľ¨è¿ĩ渡
    -0.25
    .sal
    -0.24
     internals
    -0.24
    ughty
    -0.24
    认è¯Ĩ
    -0.24
    ivers
    -0.23
    POSITIVE LOGITS
    Posted
    0.28
    ä½łè¯´
    0.26
    _almost
    0.25
    .Align
    0.25
     Ok
    0.24
    çļĦè¯Ŀ
    0.23
     HEADER
    0.23
    efined
    0.23
    csi
    0.23
    è¿Ļ段
    0.23
    Activations Density 70.744%

    No Known Activations