© 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. 22-TRANSCODER-HP
    7. 97204
    Prev
    Next
    INDEX
    Explanations

    prepositions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     things
    -0.33
     fundamentals
    -0.30
    ä»Ģä¹Īä¸ľè¥¿
    -0.29
    ä»Ģä¹Īäºĭæĥħ
    -0.28
    bane
    -0.27
     giants
    -0.27
    è¾ľ
    -0.27
    atories
    -0.27
    umbing
    -0.27
     basics
    -0.26
    POSITIVE LOGITS
    EMON
    0.28
    æ¶Ĥ
    0.25
    éĵĤ
    0.25
    amin
    0.25
    客æĪ·çļĦ
    0.24
    amon
    0.24
    äºĨä¸Ģ份
    0.23
    CONN
    0.23
    åŃĺåľ¨ä¸Ģå®ļ
    0.23
    Question
    0.23
    Activations Density 0.009%

    No Known Activations