© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 22-TRANSCODER-HP
    7. 112773
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    两æĿ¡
    -0.25
    	opt
    -0.24
    éĹ®æĪij
    -0.24
    (frame
    -0.23
     dut
    -0.23
    ias
    -0.23
     Pill
    -0.23
     parti
    -0.22
    columnName
    -0.22
    ä¸Ģ群人
    -0.22
    POSITIVE LOGITS
    æIJ¶
    0.28
    æĬ¢
    0.26
    ä¿Ŀ
    0.24
     whole
    0.23
     Whole
    0.23
    çĽĺ
    0.23
    æķ´ä½ĵ
    0.23
    _INCLUDED
    0.23
    å·©
    0.22
    infeld
    0.22
    Activations Density 0.002%

    No Known Activations

    This feature has no known activations.