© 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. 6818
    Prev
    Next
    INDEX
    Explanations

    math and science

    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
     Venezuelan
    -0.24
    fab
    -0.24
    çĮĿ
    -0.24
    çIJī
    -0.23
    ¶ļ
    -0.23
    çĶ¦
    -0.23
    erialization
    -0.23
    製
    -0.23
    çijľ
    -0.23
    æĸ¼
    -0.23
    POSITIVE LOGITS
    è¯Ŀé¢ĺ
    0.28
    çĽijå¯Ł
    0.25
    è´¨éĩı
    0.25
    è®®
    0.24
     chaud
    0.24
     Damien
    0.24
     Pitt
    0.24
     tuned
    0.24
    мÑĭ
    0.24
    mania
    0.24
    Activations Density 0.012%

    No Known Activations