© 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. 130213
    Prev
    Next
    INDEX
    Explanations

    Referring to preceding text

    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
    ä¸ªé¡¹çĽ®
    -0.30
    çļĦä½ľåĵģ
    -0.28
    纶
    -0.27
    åį±
    -0.26
    ç»Ļ她
    -0.26
    æĮĩåĩº
    -0.25
    èįĴ
    -0.25
    ynes
    -0.25
     trophies
    -0.25
    ä¸Ģ头
    -0.25
    POSITIVE LOGITS
     Function
    0.26
    maid
    0.26
    å°ļ
    0.26
    _Function
    0.25
    Table
    0.25
     Äijôi
    0.25
     strat
    0.24
     Table
    0.24
    çĿĽ
    0.24
    æĬĸ
    0.24
    Activations Density 25.478%

    No Known Activations