© 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. 31-TRANSCODER-HP
    7. 19741
    Prev
    Next
    INDEX
    Explanations

    separate

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_31.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.31.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    åĪĩ
    -0.32
    ornment
    -0.30
    ummer
    -0.28
    æ°´éĿ¢
    -0.28
    èĢĮåĩº
    -0.27
     outlet
    -0.27
    룬
    -0.25
    lette
    -0.25
    loff
    -0.25
    åĪĩæĪIJ
    -0.24
    POSITIVE LOGITS
    çľ¼éĩĮ
    0.28
    дав
    0.26
    ials
    0.26
    Bg
    0.26
    URAL
    0.25
    OST
    0.24
     Hv
    0.23
    ê¸ī
    0.23
    ground
    0.23
     prise
    0.23
    Activations Density 12.955%

    No Known Activations