© 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. 33-TRANSCODER-HP
    7. 53319
    Prev
    Next
    INDEX
    Explanations

    wet

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Clipboard
    -0.32
    aja
    -0.28
     Email
    -0.28
     Research
    -0.27
    9
    -0.26
    [email
    -0.26
     Rectangle
    -0.26
    æĹĹèĪ°
    -0.26
    .toast
    -0.26
     Ho
    -0.26
    POSITIVE LOGITS
    well
    0.36
    -pack
    0.32
    ä¸Ģå¹´ä¸Ģ度
    0.30
    eren
    0.28
    -period
    0.28
    -faced
    0.28
    wares
    0.28
    rooms
    0.27
    -flow
    0.27
    clo
    0.27
    Activations Density 0.006%

    No Known Activations