© 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. 95348
    Prev
    Next
    INDEX
    Explanations

    math expressions

    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
    ä¸¤å¼ł
    -0.27
     combined
    -0.26
    iazza
    -0.25
    袱
    -0.24
     crowds
    -0.24
    åĮħåĮħ
    -0.23
     laughter
    -0.23
    ứ
    -0.23
     sheds
    -0.23
     participating
    -0.23
    POSITIVE LOGITS
    ament
    0.29
    æѦ
    0.28
     GroÃŁ
    0.27
    acy
    0.27
    omatic
    0.26
    noon
    0.26
    íħľ
    0.25
     ado
    0.25
    ев
    0.25
    ture
    0.24
    Activations Density 0.175%

    No Known Activations