© 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. 9-TRANSCODER-HP
    7. 29457
    Prev
    Next
    INDEX
    Explanations

    lent

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_9.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.9.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    涨
    -0.29
    shal
    -0.29
    channel
    -0.26
    fest
    -0.25
    zin
    -0.24
    ponder
    -0.24
     Provid
    -0.23
    èģĶèµĽ
    -0.23
    sp
    -0.23
    клон
    -0.23
    POSITIVE LOGITS
    iffe
    0.27
    æĭĪ
    0.27
    åİŁèijĹ
    0.26
    åķ®
    0.25
     Theft
    0.25
     apples
    0.25
    Å¡t
    0.25
     fitting
    0.25
     theft
    0.24
    å¸Ŀ
    0.24
    Activations Density 4.674%

    No Known Activations