© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 6708
    Prev
    Next
    INDEX
    Explanations

    dates, numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    аем
    -0.27
    ĽĦ
    -0.26
    redicate
    -0.25
    çĽĶ
    -0.25
     uncomment
    -0.25
    IPH
    -0.25
    Ãłi
    -0.24
    墩
    -0.24
    赤
    -0.24
    undry
    -0.23
    POSITIVE LOGITS
     Portions
    0.30
    otte
    0.27
    âĪ
    0.26
    pitch
    0.25
     Trend
    0.24
    èĦĸ
    0.24
    çļĦèĦļæŃ¥
    0.24
     Exclude
    0.24
    expo
    0.24
     besides
    0.23
    Activations Density 0.434%

    No Known Activations