© 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. 163078
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    hari
    -0.26
    _taken
    -0.26
    èľĹ
    -0.26
    å¯Ħ
    -0.26
     sinon
    -0.24
    为代表
    -0.24
    为é¦ĸ
    -0.24
    èĢĮæĺ¯
    -0.24
    æĭĴç»Ŀ
    -0.24
    å·§å¦Ļ
    -0.23
    POSITIVE LOGITS
     Peggy
    0.23
     fit
    0.23
    erness
    0.23
    atto
    0.22
     ssl
    0.22
    裴
    0.22
     callable
    0.22
    ynes
    0.22
    enet
    0.22
    arial
    0.22
    Activations Density 0.001%

    No Known Activations

    This feature has no known activations.