© 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. 23-TRANSCODER-HP
    7. 25308
    Prev
    Next
    INDEX
    Explanations

    Medical/technical abbreviations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     subparagraph
    -0.29
     Sadd
    -0.26
    tog
    -0.25
    ts
    -0.24
    isible
    -0.24
    hesion
    -0.24
    autoload
    -0.23
    ividad
    -0.23
     Dems
    -0.23
    ÑĤе
    -0.23
    POSITIVE LOGITS
    æĿĢ
    0.26
     poisoning
    0.24
    ħ§
    0.24
    ä¼ļå¼ķèµ·
    0.24
     northeast
    0.24
     werden
    0.24
    é½IJé²ģ
    0.23
    åĪĨå±Ģ
    0.23
     máu
    0.23
    ubber
    0.23
    Activations Density 0.024%

    No Known Activations