© 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. 25-TRANSCODER-HP
    7. 107171
    Prev
    Next
    INDEX
    Explanations

    Electrical power systems

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     colder
    -0.27
     Spin
    -0.27
    lever
    -0.26
    à®´
    -0.26
    桶
    -0.25
    ä¿¡ç®±
    -0.25
    gar
    -0.25
    eh
    -0.25
    BEST
    -0.25
    IGH
    -0.24
    POSITIVE LOGITS
    åı¬
    0.28
    çĶµç½ij
    0.27
    iliar
    0.26
    åĭķçī©
    0.26
    ä¸ī项
    0.26
     Transformers
    0.26
    çĶµä»·
    0.25
     Tanz
    0.25
    _DP
    0.25
    åIJĪæł¼
    0.25
    Activations Density 0.923%

    No Known Activations