© 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. 56710
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    Not in Any Lists

    No Comments

    Negative Logits
     Suc
    -0.28
    æĬī
    -0.26
    åħ´è¶£
    -0.25
    wiki
    -0.24
    ToDo
    -0.24
    liga
    -0.23
    奥æĸ¯åį¡
    -0.23
     forget
    -0.23
    addon
    -0.23
    åĶ¯ä¸Ģ
    -0.23
    POSITIVE LOGITS
     cooperating
    0.26
    éĢłæĪIJçļĦ
    0.26
     cooperate
    0.26
    åĽ½æľīèµĦ产
    0.25
    SHARE
    0.24
    shares
    0.24
    etadata
    0.24
    çĿĽ
    0.24
     Decode
    0.24
    Ùĥب
    0.24
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.