© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 8427
    Prev
    Next
    INDEX
    Explanations

    argumentative text

    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
    åľĪ
    -0.25
    &E
    -0.25
     unexpected
    -0.24
     sud
    -0.24
    south
    -0.23
     nons
    -0.23
     ostat
    -0.23
    æĭ¿åĩºæĿ¥
    -0.23
     Eff
    -0.23
     jour
    -0.23
    POSITIVE LOGITS
     outweigh
    0.35
     overall
    0.33
    overall
    0.31
     dominates
    0.30
     dominance
    0.30
    edException
    0.29
    Overall
    0.28
    ä¸į平衡
    0.28
    æĢ»ä½ĵ
    0.28
     dominated
    0.28
    Activations Density 0.067%

    No Known Activations