© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 27-TRANSCODER-HP
    7. 8861
    Prev
    Next
    INDEX
    Explanations

    Shades of red

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    verted
    -0.25
     Kare
    -0.24
    Authenticated
    -0.24
    å··
    -0.24
    onet
    -0.24
     Minor
    -0.24
    aken
    -0.24
    raf
    -0.23
    åľĪåŃIJ
    -0.23
    亿ä¸ĩ
    -0.23
    POSITIVE LOGITS
    çıł
    0.28
    åĴĮ个人
    0.28
    饱
    0.26
    端åįĪ
    0.25
     Pessoa
    0.25
    å¼ķè¿Ľ
    0.25
    åºĨåħ¸
    0.25
    ouv
    0.24
     supers
    0.24
    acock
    0.24
    Activations Density 0.016%

    No Known Activations