© 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. 56566
    Prev
    Next
    INDEX
    Explanations

    Code and programming text

    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
    ismo
    -0.26
    NEL
    -0.25
    اÙģت
    -0.25
     Navigator
    -0.25
    tit
    -0.24
     browse
    -0.24
    èħĬ
    -0.24
     sentinel
    -0.24
     bal
    -0.24
    ä¹İ
    -0.24
    POSITIVE LOGITS
    åįķçĭ¬
    0.29
    statt
    0.27
    soap
    0.26
    çĭ¬ç«ĭ
    0.26
    åī¥ç¦»
    0.25
     Separate
    0.25
    lod
    0.25
    æĿ¾
    0.25
     separately
    0.24
    arez
    0.24
    Activations Density 0.002%

    No Known Activations