© 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. 107155
    Prev
    Next
    INDEX
    Explanations

    Sudden, disruptive events

    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
    nable
    -0.28
    aligned
    -0.28
    æĸ½
    -0.27
    è´Łæĭħ
    -0.27
     Ville
    -0.26
    "
    -0.26
     Banana
    -0.25
     antigen
    -0.25
     know
    -0.25
    æŁ¥æĺİ
    -0.25
    POSITIVE LOGITS
    åĨįåĪ°
    0.29
    elda
    0.28
    è½°
    0.28
    AllWindows
    0.27
    代åĬŀ
    0.27
    åIJĦçķĮ
    0.26
    åĵģè´¨
    0.26
    WINDOWS
    0.25
    妯
    0.25
     Ips
    0.25
    Activations Density 0.068%

    No Known Activations