© 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. 27-TRANSCODER-HP
    7. 7907
    Prev
    Next
    INDEX
    Explanations

    Accuracy and precision

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    éªĪ
    -0.31
    vfs
    -0.27
    cape
    -0.27
    roe
    -0.25
    chein
    -0.24
     boil
    -0.24
    è¬ĩ
    -0.24
    mons
    -0.24
    fragment
    -0.24
    ifu
    -0.24
    POSITIVE LOGITS
     precision
    1.17
    精度
    1.16
     accuracy
    1.13
    precision
    1.06
    精确
    1.04
     Precision
    1.00
    accuracy
    0.99
    Precision
    0.98
     Accuracy
    0.98
    ç²¾åĩĨ
    0.98
    Activations Density 0.013%

    No Known Activations