© 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. 95018
    Prev
    Next
    INDEX
    Explanations

    iens

    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
    intree
    -0.28
    带走
    -0.28
    lash
    -0.26
    coes
    -0.25
    说å®ŀ
    -0.24
     dried
    -0.24
    ilio
    -0.24
    ãģ¯ãģļ
    -0.23
    示æĦı
    -0.23
    bing
    -0.23
    POSITIVE LOGITS
    meter
    0.29
    ä¸ŃéĹ´
    0.27
    _meter
    0.27
    èµŃ
    0.27
     Meter
    0.27
     Bundy
    0.26
    .getAmount
    0.26
    unicode
    0.25
    wire
    0.25
    Meter
    0.25
    Activations Density 0.882%

    No Known Activations