© 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. 58547
    Prev
    Next
    INDEX
    Explanations

    Religious Indian terms

    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
    åıijå±ķéĺ¶æ®µ
    -0.27
     Mate
    -0.27
    inness
    -0.25
    DOI
    -0.24
     Gesch
    -0.24
    .UR
    -0.24
    ä¸İåıijå±ķ
    -0.23
    缸
    -0.23
    velopment
    -0.23
     subscribe
    -0.23
    POSITIVE LOGITS
    尺度
    0.27
    },'
    0.26
    ä»ĸ们ä¼ļ
    0.25
    ķĮ
    0.25
    Sizer
    0.25
     $?
    0.25
    azar
    0.25
    æºĨ
    0.25
    Ñĥл
    0.24
    ****↵
    0.24
    Activations Density 0.003%

    No Known Activations