© 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. 130873
    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
    nel
    -0.28
    NEL
    -0.27
    quarters
    -0.24
    .track
    -0.24
    以èī²
    -0.23
    çĶ¨èĩªå·±çļĦ
    -0.23
    åŁİå¸Ĥåıijå±ķ
    -0.23
    imb
    -0.23
    uel
    -0.22
    odus
    -0.22
    POSITIVE LOGITS
     classifiers
    0.25
    Ĩµ
    0.25
    /wiki
    0.25
    eve
    0.25
     assemblies
    0.25
     DISCLAIMER
    0.24
    ç»ĪçĶŁ
    0.24
    -len
    0.24
    å¢ŀåĢ¼æľįåĬ¡
    0.23
     Bos
    0.23
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.