© 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. 161936
    Prev
    Next
    INDEX
    Explanations

    Months

    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
    åīĤ
    -0.29
    è¾ĺ
    -0.28
    cin
    -0.28
    ih
    -0.27
    cwd
    -0.26
    ä¸ĭçļĦ
    -0.26
    hos
    -0.26
    ä¹ĭäºĭ
    -0.26
    ugi
    -0.25
    åīį身
    -0.25
    POSITIVE LOGITS
    åij¨æľŁ
    0.27
     middle
    0.26
     Spe
    0.25
     timers
    0.24
    ä¸ŃæľŁ
    0.24
    ewe
    0.24
    -middle
    0.24
     cycles
    0.24
    oggler
    0.24
    oon
    0.23
    Activations Density 0.012%

    No Known Activations