© 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. 20-TRANSCODER-HP
    7. 62578
    Prev
    Next
    INDEX
    Explanations

    technical texts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    olics
    -0.27
    çĥŃå¿ĥ
    -0.27
    æ¶īåıĬ
    -0.26
    å¾Ī好çļĦ
    -0.25
    éĢĤå½ĵçļĦ
    -0.25
    oor
    -0.25
    Al
    -0.25
    èĤ¯å®ļ
    -0.25
    æŀģ
    -0.24
    稳å®ļçļĦ
    -0.24
    POSITIVE LOGITS
    åıĺå¾ĹæĽ´åĬł
    0.37
    ä¸įå¦Ĥ
    0.33
     compared
    0.32
    åıĺå¾ĹæĽ´
    0.32
    æľīæĽ´å¤ļçļĦ
    0.31
     formerly
    0.31
    缸æ¯Ķä¹ĭä¸ĭ
    0.30
    缸è¾ĥ
    0.29
    缸æ¯Ķ
    0.29
    æĽ´èĥ½
    0.29
    Activations Density 61.489%

    No Known Activations