© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 22-TRANSCODER-HP
    7. 128947
    Prev
    Next
    INDEX
    Explanations

    Words ending in "ed"

    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
    Negative Logits
    ãģ¨ãģĦãģĨãĤĤãģ®
    -0.30
    uming
    -0.29
     __________________↵↵
    -0.28
    >[↵
    -0.26
    èĤ²
    -0.25
    ",__
    -0.24
    æ±°
    -0.24
    )?$
    -0.24
    ",[
    -0.24
    urga
    -0.24
    POSITIVE LOGITS
    ent
    0.28
    罩
    0.26
    åĵŃæ³£
    0.25
    imp
    0.24
    c
    0.24
    åŁºéĩij份é¢Ŀ
    0.24
    ....
    0.24
    å¸ĤæĶ¿åºľ
    0.24
    _imp
    0.24
     ent
    0.24
    Activations Density 0.059%

    No Known Activations