© 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. 7241
    Prev
    Next
    INDEX
    Explanations

    Punctuation and the number 5

    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
    ä¸įæľį
    -0.28
    nown
    -0.28
    icit
    -0.28
    logen
    -0.26
     dealloc
    -0.26
    бÑĥд
    -0.25
    .ci
    -0.25
    éħ£
    -0.25
    è´»
    -0.25
    athi
    -0.24
    POSITIVE LOGITS
    大家åĪĨ享
    0.28
    åĽĽæĺ¯
    0.27
     lòng
    0.25
    indre
    0.24
    伦æķ¦
    0.24
     dotyczÄħce
    0.23
    æ²ļ
    0.23
    ä¼ĺåħĪ
    0.23
    宫
    0.23
    аÑĨиÑı
    0.23
    Activations Density 0.003%

    No Known Activations