© 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. 97104
    Prev
    Next
    INDEX
    Explanations

    Code snippets

    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
    ot
    -0.28
     text
    -0.28
    text
    -0.26
    binding
    -0.26
     wy
    -0.26
    .execute
    -0.26
    ose
    -0.26
     customs
    -0.25
    ing
    -0.25
    otics
    -0.25
    POSITIVE LOGITS
    ForResource
    0.30
     organised
    0.29
    WithTitle
    0.28
    æłħ
    0.28
    æĬ±åĽ¢
    0.27
    æ®Ĩ
    0.26
    stile
    0.26
    ä¸įçĦ¶
    0.25
        ↵    ↵    ↵    ↵
    0.24
     organisation
    0.24
    Activations Density 0.001%

    No Known Activations