© 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. 96125
    Prev
    Next
    INDEX
    Explanations

    non-English, technical text

    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
    æµģç¨ĭ
    -0.56
     workflow
    -0.49
     flows
    -0.44
     flow
    -0.43
     workflows
    -0.41
    Workflow
    -0.39
    .Flow
    -0.38
    flow
    -0.38
    workflow
    -0.37
     Workflow
    -0.37
    POSITIVE LOGITS
    оÑĩек
    0.26
    亿ä¸ĩ
    0.25
    eah
    0.24
    åĥı个
    0.24
     GObject
    0.24
    resa
    0.24
    íĮIJ
    0.24
    DBC
    0.23
    çļĦè¯Ńè¨Ģ
    0.23
    illion
    0.23
    Activations Density 0.884%

    No Known Activations