© 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. 22-TRANSCODER-HP
    7. 99062
    Prev
    Next
    INDEX
    Explanations

    Conversational text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    ç»Ĭ
    -0.27
    è¿Ļ个人
    -0.26
     Bord
    -0.25
    åħ³éĶ®æĺ¯
    -0.25
    bridge
    -0.25
    å®ŀè´¨æĢ§
    -0.25
    纵深
    -0.25
    æĺİ天
    -0.25
    å°ĨæĮģç»Ń
    -0.25
    etak
    -0.24
    POSITIVE LOGITS
    ¡°
    0.25
    äºĽ
    0.25
    äºĨåĩł
    0.25
    =o
    0.24
    idenav
    0.24
    unal
    0.23
    )init
    0.23
     |\
    0.23
    infos
    0.23
    ,**
    0.23
    Activations Density 0.004%

    No Known Activations