© 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. 30-TRANSCODER-HP
    7. 94961
    Prev
    Next
    INDEX
    Explanations

    human

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    人类
    -0.40
     human
    -0.34
     humans
    -0.33
    èĩªçĦ¶
    -0.32
     natural
    -0.32
    åĪ«è¯´
    -0.31
    人åĬĽ
    -0.31
     Natural
    -0.29
    åĪ«
    -0.29
    human
    -0.28
    POSITIVE LOGITS
     action
    0.41
    è¡ĮåĬ¨
    0.37
     actions
    0.35
     activity
    0.35
     Activity
    0.35
    .action
    0.34
    	action
    0.34
     Action
    0.34
    æ´»è·ĥ
    0.33
    _action
    0.32
    Activations Density 0.884%

    No Known Activations