© 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. 99145
    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
    被害
    -0.26
    reinterpret
    -0.25
    模èĮĥ
    -0.25
    åħ¨æĹ¥åĪ¶
    -0.25
     afterward
    -0.25
    _BUS
    -0.25
    æłĩ
    -0.24
     obligatory
    -0.24
    强çĥĪ
    -0.24
    ç®Ģ缴
    -0.24
    POSITIVE LOGITS
    ibility
    0.27
    .Failure
    0.26
    onis
    0.25
    -ph
    0.25
    ÙĪص
    0.25
     densities
    0.25
    locker
    0.24
    àªī
    0.24
     Rodney
    0.24
    riers
    0.24
    Activations Density 0.029%

    No Known Activations

    This feature has no known activations.