© 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. 30-TRANSCODER-HP
    7. 97125
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    åĪ°è¿ĻéĩĮ
    -0.26
    oga
    -0.26
    æĽ´å¤ļä¿¡æģ¯
    -0.26
    åľ¨è¿ĻéĩĮ
    -0.26
    __('
    -0.25
    caps
    -0.25
    éĿĪ
    -0.25
     Caps
    -0.25
    主ä¹īæĢĿæĥ³
    -0.25
    æĹłå£°
    -0.25
    POSITIVE LOGITS
    mise
    0.27
     giriÅŁ
    0.27
    пÑĥÑģк
    0.26
    icine
    0.26
     passer
    0.25
    åħ¥éŨ
    0.24
    ...]
    0.24
     ||=
    0.24
    è²Į
    0.23
     resale
    0.23
    Activations Density 0.101%

    No Known Activations

    This feature has no known activations.