© 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. 41393
    Prev
    Next
    INDEX
    Explanations

    brain

    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
    thé
    -0.28
     ogl
    -0.27
    huge
    -0.24
    æķĸ
    -0.24
    metic
    -0.24
    .AddRange
    -0.24
     chir
    -0.23
     VS
    -0.23
     vacuum
    -0.23
    èĻº
    -0.23
    POSITIVE LOGITS
     brain
    0.36
    brain
    0.34
    èĦij
    0.34
    arna
    0.31
     Brain
    0.28
    arn
    0.28
    ware
    0.28
    èħ¦
    0.27
    æ´»
    0.27
     neuron
    0.27
    Activations Density 0.002%

    No Known Activations