© 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. 97145
    Prev
    Next
    INDEX
    Explanations

    open or close

    np_max-act-logits · gemini-2.0-flash
    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
     Masters
    -0.26
    èĢģå¸Ī们
    -0.25
     Honour
    -0.24
    çłĶ究人åijĺ
    -0.24
    çĶŁæ´»çļĦ
    -0.24
    ä¸ŃæľŁ
    -0.24
    æĩ¿
    -0.24
    setType
    -0.23
     Reached
    -0.23
     Visitors
    -0.23
    POSITIVE LOGITS
    éŨçªĹ
    0.28
    éŨ
    0.28
     gates
    0.27
     discussion
    0.27
    éĹ¨æ§Ľ
    0.26
    -package
    0.26
     doors
    0.26
     fields
    0.26
    åĨ¤
    0.26
    лÑĮн
    0.26
    Activations Density 0.889%

    No Known Activations