© 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. 107472
    Prev
    Next
    INDEX
    Explanations

    Research studies and statistics

    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
    å¤Ļ
    -0.27
    .Full
    -0.25
    LOTS
    -0.24
    _FULL
    -0.24
    çīĪæľ¬
    -0.24
    adar
    -0.24
    è§ĦåĪĴ
    -0.23
     sites
    -0.23
    omid
    -0.23
    odos
    -0.23
    POSITIVE LOGITS
    doc
    0.33
    约åįł
    0.28
    enerative
    0.27
    signin
    0.26
    ä¼ļè®©ä½ł
    0.26
     aproxim
    0.25
    ç²¾é«ĵ
    0.25
    Doc
    0.25
    ãģ¨ãģĦãģĨãĤĤãģ®
    0.24
     doc
    0.24
    Activations Density 5.301%

    No Known Activations