© 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. 43029
    Prev
    Next
    INDEX
    Explanations

    for loops (programming)

    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
    èĢĮ
    -1.46
     while
    -1.16
    èĢĮåľ¨
    -1.09
    while
    -1.08
     whereas
    -1.01
    	while
    -0.94
     While
    -0.92
    While
    -0.91
     whilst
    -0.91
    èĢĮåĩº
    -0.88
    POSITIVE LOGITS
    \Bridge
    0.28
    ksen
    0.28
    =?,
    0.25
    .animations
    0.24
    า
    0.23
    adoo
    0.23
    .mixin
    0.23
    âĺī
    0.22
    otime
    0.22
     sor
    0.22
    Activations Density 0.007%

    No Known Activations