© 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. 7474
    Prev
    Next
    INDEX
    Explanations

    the number 2

    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
     pursued
    -0.27
     —↵↵
    -0.27
    dbcTemplate
    -0.26
     onSelect
    -0.26
    iral
    -0.26
    è·¸
    -0.25
     borne
    -0.25
    ä½ı
    -0.25
    verages
    -0.24
    ered
    -0.24
    POSITIVE LOGITS
    akh
    0.26
     PROFITS
    0.25
    Mont
    0.24
    è¿ĺæľīä»Ģä¹Ī
    0.24
    åijķåIJIJ
    0.23
    æ¸Ŀ
    0.23
    ä¼ļæľī
    0.23
    ÑĮÑı
    0.23
    day
    0.23
    éĢĢä¼ij
    0.22
    Activations Density 0.104%

    No Known Activations