© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 25-TRANSCODER-HP
    7. 107035
    Prev
    Next
    INDEX
    Explanations

    Article/name snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    èIJ¥è¿IJ
    -0.28
    ä¹ĭäºĭ
    -0.26
    è¥Ħ
    -0.25
    çĻ½éĽª
    -0.25
    cec
    -0.25
    ruz
    -0.24
    åħ¨éķĩ
    -0.24
     woods
    -0.24
    orc
    -0.23
    ä»Ģä¹Īæł·çļĦ
    -0.23
    POSITIVE LOGITS
    unch
    0.27
    ula
    0.26
     remot
    0.26
    ULA
    0.26
     consumer
    0.26
     pot
    0.25
    ê³ł
    0.25
    çķĻä½ı
    0.25
     dispens
    0.25
    owers
    0.24
    Activations Density 0.029%

    No Known Activations