© 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. 32-TRANSCODER-HP
    7. 42952
    Prev
    Next
    INDEX
    Explanations

    people and professions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     callers
    -0.38
    éĺŁåijĺ们
    -0.31
     legislators
    -0.29
     UserDao
    -0.29
     subscribers
    -0.28
     politicians
    -0.28
     planners
    -0.28
     lawmakers
    -0.27
     inspectors
    -0.27
     advertisers
    -0.27
    POSITIVE LOGITS
     student
    0.37
    student
    0.32
    elp
    0.28
    çļĦåѦçĶŁ
    0.28
    Student
    0.27
     textbooks
    0.27
    çĶŁ
    0.27
    æĬĽ
    0.27
    |^
    0.26
    çĶĺ
    0.26
    Activations Density 0.001%

    No Known Activations