© 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. 30-TRANSCODER-HP
    7. 96039
    Prev
    Next
    INDEX
    Explanations

    new

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bedo
    -0.25
    âĺĽ
    -0.23
    âĩij
    -0.23
    _INCLUDED
    -0.21
    esome
    -0.21
    icrosoft
    -0.21
    ëĵľë¦¬
    -0.21
    onis
    -0.20
    noc
    -0.20
    æľ¬æĬ¥
    -0.20
    POSITIVE LOGITS
     new
    1.79
    æĸ°çļĦ
    1.64
    new
    1.55
    æĸ°
    1.55
    çļĦæĸ°
    1.42
    .new
    1.34
    (new
    1.34
    æĸ°ãģĹãģĦ
    1.30
    	new
    1.29
    -new
    1.29
    Activations Density 0.917%

    No Known Activations