© 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. 23-TRANSCODER-HP
    7. 23410
    Prev
    Next
    INDEX
    Explanations

    public

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    onso
    -0.26
     representations
    -0.26
    controllers
    -0.25
     versions
    -0.25
     save
    -0.24
     adopt
    -0.24
     Granny
    -0.24
    online
    -0.24
     Lib
    -0.24
     Adopt
    -0.24
    POSITIVE LOGITS
    åįģåĪĨéĩįè¦ģ
    0.31
    éļ¾é¢ĺ
    0.30
     matter
    0.29
    çļĦéĩį大
    0.28
    éĿŀ常éĩįè¦ģ
    0.28
    åĢ¼å¾Ĺåħ³æ³¨
    0.27
    çļĦæĪĺçķ¥
    0.26
     Matter
    0.26
    matter
    0.26
    ListItem
    0.25
    Activations Density 0.009%

    No Known Activations