© 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. 97065
    Prev
    Next
    INDEX
    Explanations

    RNA

    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
    agu
    -0.28
    æ±Ģ
    -0.27
    orc
    -0.26
     integrate
    -0.25
     incorporating
    -0.25
    ty
    -0.24
     integration
    -0.24
     incorpor
    -0.24
    å»·
    -0.24
    rac
    -0.23
    POSITIVE LOGITS
     RN
    0.63
    RN
    0.61
     RNA
    0.61
    RNA
    0.57
    rna
    0.46
     messenger
    0.46
     mRNA
    0.45
    ARN
    0.44
    rn
    0.42
    ï¼²
    0.41
    Activations Density 0.896%

    No Known Activations