© 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. 27-TRANSCODER-HP
    7. 58593
    Prev
    Next
    INDEX
    Explanations

    Code and legal language

    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
    Negative Logits
    家ä½ı
    -0.26
    åħ¬åı¸åľ¨
    -0.25
    ï¼ŁãĢį
    -0.25
     Birds
    -0.25
    tors
    -0.25
    çļĦ帮åĬ©ä¸ĭ
    -0.25
    èĬ±å¼Ģ
    -0.24
    产ä¸ļåıijå±ķ
    -0.24
    idas
    -0.24
    )","
    -0.24
    POSITIVE LOGITS
    eve
    0.28
    OLA
    0.27
     entirety
    0.25
    åıĺå½¢
    0.25
    getQuery
    0.25
    umb
    0.24
    yor
    0.24
    cap
    0.24
    obe
    0.24
    å¢ĥ
    0.24
    Activations Density 0.002%

    No Known Activations