© 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. 97159
    Prev
    Next
    INDEX
    Explanations

    engines and electricity

    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
    踣
    -0.28
    codegen
    -0.28
     waking
    -0.25
     Hogan
    -0.25
    Pipe
    -0.25
    itor
    -0.24
    åºĬ
    -0.24
     fri
    -0.24
    FRING
    -0.23
    綾åIJĪ
    -0.23
    POSITIVE LOGITS
    çĶµåĬ¨
    0.60
     electric
    0.54
    缴æµģ
    0.52
     DC
    0.47
     engine
    0.47
     engines
    0.47
    åıijåĬ¨æľº
    0.45
     dc
    0.44
     Electric
    0.44
    Electric
    0.41
    Activations Density 1.077%

    No Known Activations