© 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. 19-TRANSCODER-HP
    7. 9326
    Prev
    Next
    INDEX
    Explanations

    Negation and disagreement

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ece
    -0.29
    ãģ¾ãģĦ
    -0.27
    setParameter
    -0.26
     directive
    -0.26
    roy
    -0.26
     labeled
    -0.25
    笼
    -0.25
    cade
    -0.24
    åºĦ
    -0.24
    åIJŀ
    -0.24
    POSITIVE LOGITS
    -che
    0.33
    pdata
    0.29
    æ²Ļ滩
    0.27
    åİĿ
    0.27
     Signs
    0.26
    anel
    0.25
    ðŁĺĤ
    0.25
     Steps
    0.24
    landers
    0.24
    æĸ¹æĸ¹éĿ¢éĿ¢
    0.24
    Activations Density 0.029%

    No Known Activations