© 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. 20-TRANSCODER-HP
    7. 129133
    Prev
    Next
    INDEX
    Explanations

    that

    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
    Negative Logits
     cameo
    -0.27
    åı£æ°Ķ
    -0.26
    notated
    -0.26
    æĹ¥çĶµ
    -0.26
     chiếu
    -0.25
    çļĦçľ¼
    -0.25
     lÆ°á»Ľi
    -0.25
    oro
    -0.25
    æĥħåķĨ
    -0.24
    jb
    -0.24
    POSITIVE LOGITS
    room
    0.31
    æijĩ
    0.29
    scr
    0.28
     scr
    0.28
     room
    0.28
     practicing
    0.26
    aron
    0.25
    æīĪ
    0.25
     roku
    0.25
    è¿ĻäºĽéĹ®é¢ĺ
    0.25
    Activations Density 1.666%

    No Known Activations