© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 7371
    Prev
    Next
    INDEX
    Explanations

    Gerunds

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    trs
    -0.28
    umo
    -0.24
    mani
    -0.24
    ä¸įå¤ļ
    -0.24
     Chip
    -0.24
    ìĿĮìĿĦ
    -0.24
    人æķ°
    -0.23
    ман
    -0.23
     moo
    -0.23
    æĪªèĩ³çĽ®åīį
    -0.23
    POSITIVE LOGITS
    IsRequired
    0.27
    oley
    0.26
    -held
    0.24
    ÑĨ
    0.24
     hass
    0.24
     vacc
    0.24
    hta
    0.23
    触
    0.23
     spare
    0.23
     star
    0.23
    Activations Density 0.072%

    No Known Activations