© 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. 107720
    Prev
    Next
    INDEX
    Explanations

    Code

    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
    letic
    -0.29
    æ¦ī
    -0.27
    archy
    -0.26
    naissance
    -0.26
    饮éħĴ
    -0.25
    åĽĽä¸ªæĸ¹éĿ¢
    -0.25
    logue
    -0.25
     Dance
    -0.24
    æĸĩæĺİ
    -0.24
    dance
    -0.24
    POSITIVE LOGITS
    èİ·æĤī
    0.28
     progressive
    0.27
    #else
    0.26
    ãģĭãģĦ
    0.26
    AXB
    0.25
    çĥŃéĩı
    0.25
     progress
    0.24
    æīįåıijçİ°
    0.24
    oron
    0.24
    IBAction
    0.23
    Activations Density 0.406%

    No Known Activations