© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 30-TRANSCODER-HP
    7. 96415
    Prev
    Next
    INDEX
    Explanations

    Animation and motion

    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
    Not in Any Lists

    No Comments

    Negative Logits
    éŃĶ鬼
    -0.25
    æİĪ
    -0.25
    å´Ľ
    -0.25
    欢è¿İæĤ¨
    -0.23
     conquest
    -0.23
    =subprocess
    -0.23
    ushi
    -0.23
     crest
    -0.23
    uste
    -0.23
    æĸĩåĮĸæĹħ游
    -0.22
    POSITIVE LOGITS
     motion
    0.54
     Motion
    0.50
     animation
    0.49
    anim
    0.48
     moc
    0.47
    motion
    0.43
     animated
    0.43
     anim
    0.42
     animate
    0.42
     key
    0.42
    Activations Density 1.142%

    No Known Activations