© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 4758
    Prev
    Next
    INDEX
    Explanations

    Code/Technical documents

    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
    Æı
    -0.29
    åı£åı·
    -0.27
    ï¼ī↵↵
    -0.26
    ulet
    -0.25
    交代
    -0.25
    .SelectCommand
    -0.25
    ï¼ī
    -0.25
    .hasNext
    -0.24
    confirmation
    -0.24
    oftware
    -0.24
    POSITIVE LOGITS
    ç¬Ķ
    0.28
    æĭ©
    0.26
    irts
    0.26
    erval
    0.26
    inary
    0.25
    éĢ»
    0.25
    xaa
    0.24
    sheet
    0.24
    ningen
    0.24
     semiclass
    0.24
    Activations Density 0.006%

    No Known Activations