© 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. 95905
    Prev
    Next
    INDEX
    Explanations

    hospital

    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
    ç»´å¥ĩ
    -0.31
     vess
    -0.30
    andi
    -0.27
    åģľäº§
    -0.25
    åĪ¶åº¦æĶ¹éĿ©
    -0.25
    纲
    -0.25
    ett
    -0.25
    é¢ĦæĬ¥
    -0.25
    iert
    -0.24
    ä¸ĢæĬ¹
    -0.24
    POSITIVE LOGITS
     centers
    0.35
    centers
    0.34
     center
    0.33
    ä¸Ńå¿ĥ
    0.32
    (center
    0.28
     care
    0.28
    care
    0.28
     ambulance
    0.28
    çĹħæĪ¿
    0.28
    arc
    0.27
    Activations Density 0.074%

    No Known Activations