© 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. 129389
    Prev
    Next
    INDEX
    Explanations

    scientific/technical

    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
     Crowley
    -0.29
    å°ĨæĮģç»Ń
    -0.27
    lemn
    -0.26
    éĥ½åºĶ该
    -0.25
    ipur
    -0.25
    æĽ¿è¡¥
    -0.25
    plx
    -0.24
    ipeg
    -0.24
    _batches
    -0.24
    æ´Ĺ礼
    -0.24
    POSITIVE LOGITS
     Tre
    0.31
    edic
    0.30
    edia
    0.27
    空ä¸Ń
    0.26
     recur
    0.26
    .SIG
    0.26
    æľįåĬ¡åĮº
    0.25
    arat
    0.25
    okin
    0.25
    (SIG
    0.25
    Activations Density 25.252%

    No Known Activations