© 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. 23496
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    éļı
    -0.29
    鼶ç¢İ
    -0.28
    并å°Ĩ
    -0.26
    å®ļå¾ĭ
    -0.25
    åı¯ä»¥è¯´
    -0.24
    .defineProperty
    -0.23
    åľ¨æĪijçľĭæĿ¥
    -0.23
    opard
    -0.23
    ĮĢ
    -0.23
    etimes
    -0.23
    POSITIVE LOGITS
    çĸ£
    0.29
    -double
    0.28
    éļį
    0.28
    erness
    0.28
    á»ĭa
    0.26
    åłŀ
    0.26
    髯
    0.25
    мел
    0.25
    idan
    0.25
    agan
    0.24
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.