© 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. 12-TRANSCODER-HP
    7. 23842
    Prev
    Next
    INDEX
    Explanations

    gardening and planting

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    主ä¸ļ
    -0.26
    ertools
    -0.25
    lieÃŁ
    -0.25
     Bain
    -0.25
    ÑĤиÑĢ
    -0.24
    èĦī
    -0.24
    çļĦ身影
    -0.24
    traction
    -0.23
     beta
    -0.23
    assin
    -0.23
    POSITIVE LOGITS
     cursed
    0.27
     manh
    0.26
     boa
    0.25
    å¤ĦåĪĨ
    0.25
     bounced
    0.24
     thirds
    0.24
    JUnit
    0.24
    sites
    0.23
     aquarium
    0.23
    indexes
    0.23
    Activations Density 0.001%

    No Known Activations