© 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. 12-TRANSCODER-HP
    7. 22197
    Prev
    Next
    INDEX
    Explanations

    Latin suffixes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    pan
    -0.28
    åij¨è½¬
    -0.27
    cape
    -0.27
     (&
    -0.26
    ogue
    -0.26
    çĮ©
    -0.26
    ä¿Ŀè¯ģéĩij
    -0.25
    lon
    -0.25
    Lon
    -0.24
    æł¼å°Ķ
    -0.24
    POSITIVE LOGITS
    undef
    0.27
    UMENT
    0.27
    aes
    0.27
    æµ´
    0.25
    éĢĴ
    0.25
    argv
    0.24
    为客æĪ·
    0.24
    UNT
    0.24
    _except
    0.23
    åªĴ
    0.23
    Activations Density 0.006%

    No Known Activations