© 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. 19961
    Prev
    Next
    INDEX
    Explanations

    stored

    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
    é«ĺåħ´
    -0.32
    ocha
    -0.28
    quirer
    -0.26
    phis
    -0.26
    åħį责声æĺİ
    -0.26
    é®®
    -0.25
     haste
    -0.25
    -auto
    -0.25
    ires
    -0.24
     Chester
    -0.24
    POSITIVE LOGITS
     beyond
    0.32
     out
    0.29
    out
    0.28
    (Container
    0.27
    åĩº
    0.27
    (cal
    0.27
    /cal
    0.27
    	out
    0.26
    igm
    0.26
    _past
    0.26
    Activations Density 0.020%

    No Known Activations