© 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. 58510
    Prev
    Next
    INDEX
    Explanations

    will

    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
    andle
    -0.29
    çĹ£
    -0.28
     carefully
    -0.25
    eness
    -0.25
     meticulously
    -0.24
    ytt
    -0.24
    _tra
    -0.24
    èĢĥãģĪãģ¦
    -0.23
    æĴĦ
    -0.23
     patiently
    -0.23
    POSITIVE LOGITS
     sometimes
    0.33
    常
    0.32
     often
    0.32
     learning
    0.30
     glad
    0.29
    æĥĬ
    0.28
     surprised
    0.28
    è´¯éĢļ
    0.28
     Sometimes
    0.27
    è¾ĩ
    0.27
    Activations Density 0.012%

    No Known Activations