© 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. 96828
    Prev
    Next
    INDEX
    Explanations

    Internet protocols and ports

    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
     protocol
    -0.80
    åįıè®®
    -0.79
     Prot
    -0.76
     protocols
    -0.75
    protocol
    -0.72
    _protocol
    -0.68
     Protocol
    -0.65
    Protocol
    -0.65
    Prot
    -0.64
    prot
    -0.61
    POSITIVE LOGITS
    æĶ¾æīĭ
    0.30
    depart
    0.27
    _elim
    0.27
     departing
    0.25
    çľĭä»ĸ
    0.25
    mere
    0.25
     Depart
    0.24
    à¹Īาย
    0.24
     depart
    0.24
    departure
    0.23
    Activations Density 0.121%

    No Known Activations