© 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. 94899
    Prev
    Next
    INDEX
    Explanations

    Code snippets

    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
    çħ§
    -0.30
     Whisper
    -0.27
    hound
    -0.25
    unta
    -0.25
    itus
    -0.25
    BOSE
    -0.25
    ศาส
    -0.25
    æ±
    -0.24
     implied
    -0.24
    顺
    -0.24
    POSITIVE LOGITS
     disg
    0.26
    iko
    0.26
    NG
    0.25
    ign
    0.24
    å¾Ĺèµ·
    0.24
    oppers
    0.24
    uxe
    0.24
    æĿ¼
    0.24
    uez
    0.24
     Pacific
    0.24
    Activations Density 0.002%

    No Known Activations