© 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. 22-TRANSCODER-HP
    7. 112994
    Prev
    Next
    INDEX
    Explanations

    Negative situations/problems

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    å¹´ä¹ĭ
    -0.26
    hon
    -0.26
    æĹ¥æľ¬äºº
    -0.25
    ionario
    -0.25
     planning
    -0.24
    çīĪæĿĥå½ĴåİŁ
    -0.24
    aren
    -0.24
    ae
    -0.23
    乡æĿijæĹħ游
    -0.23
    æŀĦæĪIJäºĨ
    -0.23
    POSITIVE LOGITS
     presumably
    0.30
    ä¼¼
    0.30
     possibly
    0.30
     allegedly
    0.29
     purported
    0.28
     probably
    0.28
     reportedly
    0.28
    åı¯èĥ½æĺ¯
    0.28
    åı¯èĥ½
    0.28
     seemingly
    0.28
    Activations Density 0.002%

    No Known Activations