© 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. 7658
    Prev
    Next
    INDEX
    Explanations

    Conversational text

    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
    çĪ±å¥½
    -0.32
    eer
    -0.29
    umd
    -0.26
    æĹłæĦı
    -0.25
    ublisher
    -0.25
     sober
    -0.25
    ogh
    -0.25
    usc
    -0.25
    Inspectable
    -0.25
    yro
    -0.24
    POSITIVE LOGITS
    iji
    0.31
    allow
    0.28
    CUS
    0.25
    è·³
    0.25
    åħģ许
    0.25
    enny
    0.25
    باÙĨ
    0.25
    寮
    0.24
    adamente
    0.24
    éĽĨåĽ¢
    0.24
    Activations Density 0.007%

    No Known Activations