© 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. 17999
    Prev
    Next
    INDEX
    Explanations

    foreign language

    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
     v
    -0.38
     h
    -0.37
     th
    -0.36
     mal
    -0.36
     the
    -0.35
     f
    -0.35
     des
    -0.35
     an
    -0.34
     co
    -0.34
     b
    -0.34
    POSITIVE LOGITS
    Reuse
    0.35
     intox
    0.33
    ContentSize
    0.29
     altercation
    0.29
    lemn
    0.29
    iblings
    0.28
     mutating
    0.28
     Cla
    0.28
    massage
    0.28
    Fallback
    0.28
    Activations Density 4.402%

    No Known Activations