© 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. 96314
    Prev
    Next
    INDEX
    Explanations

    antibiotic-resistant bacteria

    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
    ottom
    -0.28
    .Style
    -0.27
     lettre
    -0.26
    LEG
    -0.25
    累积
    -0.25
     carry
    -0.24
    obre
    -0.24
    letter
    -0.24
     strategies
    -0.24
    GNU
    -0.24
    POSITIVE LOGITS
    å®ľå®¾
    0.29
    åĿıäºĨ
    0.28
     wym
    0.27
    èIJİ缩
    0.27
    å¹²æ¶ī
    0.26
    (require
    0.26
    ame
    0.26
     ac
    0.25
     Require
    0.25
    ici
    0.25
    Activations Density 0.005%

    No Known Activations