© 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. 25600
    Prev
    Next
    INDEX
    Explanations

    scientific/academic texts

    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
    edList
    -0.28
    çĪª
    -0.27
    åħ·
    -0.27
    acco
    -0.27
    åĩłæŃ¥
    -0.26
    è¿Ļ两ç§į
    -0.26
    åIJĦéĥ¨éŨ
    -0.24
    è¿Ļåĩłä¸ª
    -0.24
    å®ļå¾ĭ
    -0.24
    åIJĦåİ¿
    -0.24
    POSITIVE LOGITS
    åĪĻæĺ¯
    0.35
    æĺ¯ä¸Ģ个
    0.30
    æĪijçľĭ
    0.29
    æĺ¯ä¸Ģ项
    0.29
    æĺ¯ä¸Ģä½į
    0.29
     is
    0.28
    åĪĻ
    0.27
    èĢĮ
    0.27
    æĺ¯ä»¥
    0.27
     usable
    0.27
    Activations Density 0.003%

    No Known Activations