© 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. 12-TRANSCODER-HP
    7. 24267
    Prev
    Next
    INDEX
    Explanations

    Multiple different texts sources

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     dame
    -0.29
    /lic
    -0.29
    å±Ĥ次
    -0.25
     OTHERWISE
    -0.24
     Thrones
    -0.24
     MILF
    -0.24
    atism
    -0.24
    layer
    -0.24
     incomes
    -0.24
     propName
    -0.23
    POSITIVE LOGITS
    åĮħåĮħ
    0.28
    CNT
    0.28
    管è¾ĸ
    0.27
    GENER
    0.26
    ä¸įæĺ¯ä¸Ģ个
    0.25
    GC
    0.25
    ç§ijæĬĢèĤ¡ä»½
    0.24
    isz
    0.24
     Fre
    0.24
    对æłĩ
    0.23
    Activations Density 0.000%

    No Known Activations