© 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. 131071
    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
    izzes
    -0.27
    æŃ£æĸĩ
    -0.25
     Schwe
    -0.24
    æĺ¯å¤ļä¹Ī
    -0.24
     trig
    -0.24
    .dds
    -0.23
     greatly
    -0.23
    @
    -0.23
     pur
    -0.23
    plan
    -0.23
    POSITIVE LOGITS
    lator
    0.32
    楼ä¸ĭ
    0.28
    æĢ»éĥ¨
    0.28
    oby
    0.28
    usc
    0.26
    xin
    0.26
    lint
    0.25
    åij¨è¾¹
    0.24
    éļĶå£ģ
    0.23
    UTH
    0.23
    Activations Density 0.024%

    No Known Activations