© 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. 20-TRANSCODER-HP
    7. 140987
    Prev
    Next
    INDEX
    Explanations

    "to be" verb

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ikal
    -0.26
    åıĺ
    -0.25
    缴
    -0.25
     curt
    -0.24
    IAL
    -0.24
    ever
    -0.24
    NL
    -0.24
    æľĢ
    -0.24
    át
    -0.24
    neau
    -0.24
    POSITIVE LOGITS
    åİĿ
    0.29
    èĻ¹æ¡¥
    0.27
    lbrace
    0.26
    velle
    0.25
     flexGrow
    0.25
    æĺ¯åIJ¦ä¼ļ
    0.25
    orch
    0.24
    åľ¨åħ¶
    0.23
    åĵ¥ä»¬
    0.23
    tyard
    0.23
    Activations Density 18.572%

    No Known Activations