© 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. 58588
    Prev
    Next
    INDEX
    Explanations

    true

    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
     truly
    -0.30
    ss
    -0.28
     actually
    -0.27
    /drivers
    -0.27
    ington
    -0.27
    ripper
    -0.25
    çī¹è´¨
    -0.24
    actually
    -0.24
    ntax
    -0.24
    èĥª
    -0.24
    POSITIVE LOGITS
     latter
    0.29
    -handed
    0.28
    /false
    0.28
    iliar
    0.28
    -money
    0.27
    æĮij
    0.27
    æ¾Ħæ¸ħ
    0.26
    arent
    0.26
     fly
    0.26
     morning
    0.25
    Activations Density 1.319%

    No Known Activations