© 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. 95393
    Prev
    Next
    INDEX
    Explanations

    debt, deficit

    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
    çķı
    -0.29
    ä¸įæľį
    -0.27
    äºļ
    -0.27
    åħĥç´ł
    -0.27
     intern
    -0.26
    æijĩ
    -0.25
    æľ¯
    -0.25
    缣
    -0.25
    墨
    -0.25
     Bis
    -0.25
    POSITIVE LOGITS
    deal
    0.30
    iped
    0.27
    çıı
    0.25
    æ½¢
    0.25
    (cal
    0.24
    aty
    0.24
     ogs
    0.24
    atha
    0.24
     Greeks
    0.23
    -Cal
    0.23
    Activations Density 0.105%

    No Known Activations