© 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. 27-TRANSCODER-HP
    7. 9839
    Prev
    Next
    INDEX
    Explanations

    click

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    æķŀ
    -0.31
    æį¶
    -0.26
    ventions
    -0.26
     ontvang
    -0.26
    è£ħ
    -0.26
     CHIP
    -0.26
    oret
    -0.25
    (script
    -0.25
    ordion
    -0.25
     iT
    -0.24
    POSITIVE LOGITS
    mos
    0.29
    icol
    0.26
    çĶŁæ®ĸ
    0.26
     something
    0.26
    dee
    0.25
    æĺ¯ä¸Ģ件
    0.25
    à°¦
    0.25
    AndView
    0.24
     stranger
    0.24
    UCT
    0.24
    Activations Density 0.002%

    No Known Activations