© 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. 88677
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    Not in Any Lists

    No Comments

    Negative Logits
    å¥ĸéĩij
    -0.25
     LICENSE
    -0.25
    åĪĨè¡Į
    -0.25
    ä¸Ĭå¹´
    -0.24
     génér
    -0.24
    angan
    -0.24
    ä¸ĢåĪĨéĴ±
    -0.24
     Lebens
    -0.24
     Noon
    -0.23
     noon
    -0.23
    POSITIVE LOGITS
    èİł
    0.25
     Epid
    0.24
    heels
    0.24
     ord
    0.23
     [âĢ¦]
    0.23
    Ŀ¼
    0.23
    鹿
    0.23
    ird
    0.23
    á»ĩu
    0.23
     Antar
    0.23
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.