© 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. 98866
    Prev
    Next
    INDEX
    Explanations

    "to be" verb forms

    np_max-act · gemini-2.0-flash
    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
    ADE
    -0.27
    缮å½ķ
    -0.27
    ales
    -0.26
     merit
    -0.26
    æ¸ħæĺİ
    -0.26
    ##↵
    -0.26
    chè
    -0.25
    ade
    -0.25
     helper
    -0.24
    åĢ¼
    -0.24
    POSITIVE LOGITS
    ophon
    0.26
    èĥ½æĬĬ
    0.25
    èģĮä¸ļçĶŁæ¶¯
    0.25
     Technician
    0.24
    orners
    0.24
    qrt
    0.24
    pytest
    0.24
    åħ³éŨ
    0.24
    _TER
    0.24
     jeden
    0.24
    Activations Density 0.007%

    No Known Activations