© 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. 23571
    Prev
    Next
    INDEX
    Explanations

    Achieving goals, success

    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
    æķ¢
    -0.28
    woke
    -0.28
    UserService
    -0.27
    Witness
    -0.26
    took
    -0.26
    zas
    -0.26
    è¯Ńè¨Ģ
    -0.26
    大æī¹
    -0.25
    HAND
    -0.24
    odu
    -0.24
    POSITIVE LOGITS
    æĪIJ
    0.25
     cum
    0.24
    èľĺèĽĽ
    0.24
    æīĢæīĢ
    0.24
    cum
    0.23
    ä»Ģä¹Īéĥ½ä¸į
    0.23
    å®ŀçİ°
    0.23
    	Con
    0.23
     medium
    0.23
     æĪIJ
    0.23
    Activations Density 0.006%

    No Known Activations