© 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. 23589
    Prev
    Next
    INDEX
    Explanations

    Technical subjects

    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
    Negative Logits
    èµ°ä¸ĭåİ»
    -0.27
     Kensington
    -0.27
     Trophy
    -0.26
     Enlight
    -0.25
    天èĬ±
    -0.24
    çĻ½éĵ¶
    -0.24
    elight
    -0.24
    åIJĦ个çݯèĬĤ
    -0.23
    TM
    -0.23
     TM
    -0.23
    POSITIVE LOGITS
    èĤī
    0.28
    è´·
    0.27
    åĬŀ
    0.27
    alem
    0.27
    &o
    0.26
    tober
    0.25
    gos
    0.25
    ENTER
    0.24
    uyến
    0.23
    ç¹ĩ
    0.23
    Activations Density 0.082%

    No Known Activations