© 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. 97219
    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
    Negative Logits
    ÑĢажа
    -0.30
    raries
    -0.27
    ä¸Ģèĩ´æĢ§
    -0.27
    quirer
    -0.27
    ialis
    -0.25
    寰
    -0.25
    æ¯ĶåĪ©
    -0.24
     ash
    -0.24
    ÑĨиÑİ
    -0.24
     Ashe
    -0.24
    POSITIVE LOGITS
    gan
    0.27
    uj
    0.26
    uje
    0.25
    å¤©åľ°
    0.24
    eron
    0.24
    ll
    0.23
    touch
    0.23
    project
    0.23
    ibase
    0.23
    aid
    0.23
    Activations Density 0.002%

    No Known Activations

    This feature has no known activations.