© 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. 31-TRANSCODER-HP
    7. 18985
    Prev
    Next
    INDEX
    Explanations

    part or parts

    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
    Not in Any Lists

    No Comments

    Negative Logits
    worthy
    -0.28
    亮丽
    -0.25
    lixir
    -0.24
    æѤæĸĩ
    -0.24
    ipes
    -0.24
    åĶ¤
    -0.24
    xec
    -0.23
    çĦĺ
    -0.23
     outcry
    -0.22
    allee
    -0.22
    POSITIVE LOGITS
    éĥ¨åĪĨ
    1.18
     part
    1.13
     parts
    1.03
    çļĦéĥ¨åĪĨ
    0.98
    part
    0.97
     parte
    0.94
    parts
    0.93
     portion
    0.93
    ä¸Ģéĥ¨åĪĨ
    0.92
    éĥ¨ä»½
    0.91
    Activations Density 33.751%

    No Known Activations