© 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. 35-TRANSCODER-HP
    7. 40260
    Prev
    Next
    INDEX
    Explanations

    Abbreviations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_35.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.35.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    éªĩ
    -0.32
     günd
    -0.27
     metals
    -0.26
     scream
    -0.26
     pulver
    -0.26
     doom
    -0.26
    åıĺå½¢
    -0.25
     deadly
    -0.25
    çľ¼æ³ª
    -0.25
     impover
    -0.25
    POSITIVE LOGITS
     B
    0.35
     Lore
    0.29
     Technology
    0.29
     MLA
    0.29
     York
    0.28
     Mandela
    0.28
     CBD
    0.27
     RFC
    0.27
     Roosevelt
    0.27
     Buffett
    0.27
    Activations Density 16.881%

    No Known Activations