© 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. 33-TRANSCODER-HP
    7. 54588
    Prev
    Next
    INDEX
    Explanations

    nouns ending in "s"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    åħŃ个æľĪ
    -0.29
    -anchor
    -0.26
    æĺ¯æĪijçļĦ
    -0.26
    hape
    -0.26
    xic
    -0.26
    çŃı
    -0.26
    åĪĹ为
    -0.25
    ä¸įå¾Ĺ转载
    -0.25
    æĺ¯ä»ĸ
    -0.24
    æľīå¾Īå¤ļç§į
    -0.24
    POSITIVE LOGITS
     truths
    0.42
     forms
    0.41
     ends
    0.41
     desires
    0.41
     views
    0.39
     senses
    0.39
     realities
    0.39
     sounds
    0.37
     accounts
    0.36
     faces
    0.36
    Activations Density 0.047%

    No Known Activations