© 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. 18-TRANSCODER-HP
    7. 90255
    Prev
    Next
    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_18.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.18.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    icode
    -0.28
    å®ŀéĻħè¡ĮåĬ¨
    -0.26
    ök
    -0.26
    oka
    -0.25
    è¿ĺåľ¨
    -0.24
    è°ł
    -0.24
    ipel
    -0.24
    æk
    -0.24
    Uvs
    -0.24
    ipples
    -0.23
    POSITIVE LOGITS
    å±ĬæŶ
    0.33
     Ignore
    0.30
    综åIJĪ
    0.29
    ignore
    0.28
     instantaneous
    0.28
    æµ·æ£ł
    0.27
    人士
    0.27
    åĴĤ
    0.26
    å¤ļ人
    0.26
    æ¼ł
    0.26
    Activations Density 10.532%

    No Known Activations