© 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. 23-TRANSCODER-HP
    7. 163044
    Prev
    Next
    INDEX
    Explanations

    Scientific reports/news

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    容éĩı
    -0.28
    .qual
    -0.28
    quals
    -0.28
    _capacity
    -0.27
     capacity
    -0.27
     stake
    -0.26
    capacity
    -0.26
    esting
    -0.25
    aille
    -0.25
     capacities
    -0.25
    POSITIVE LOGITS
    æĺ¯æľĢ
    0.53
    ä¸ĸçķĮ第ä¸Ģ
    0.49
    æľĢéķ¿
    0.43
     longest
    0.41
    é¦ĸå¸Ń
    0.41
    第ä¸ĢåIJį
    0.41
    ä¸ŃæľĢ
    0.40
    é¦ĸå¯Į
    0.40
    æĪIJ为
    0.40
    æľĢ
    0.39
    Activations Density 0.004%

    No Known Activations