© 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. 88806
    Prev
    Next
    INDEX
    Explanations

    Diverse notations/formats

    np_max-act · gemini-2.0-flash
    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
     shared
    -0.33
    èģĶåĬ¨
    -0.28
    -shared
    -0.28
    åħ±åIJĮ
    -0.28
     jointly
    -0.28
     separat
    -0.27
    èľľ
    -0.27
    èģĶ绾
    -0.27
    åıĮè¾¹
    -0.26
     separate
    -0.26
    POSITIVE LOGITS
     taller
    0.36
     richer
    0.35
     superior
    0.34
    åīįèĢħ
    0.32
    åĬ£
    0.31
     weaker
    0.30
    agua
    0.30
    é¢ĨåħĪçļĦ
    0.29
     superiority
    0.29
     nicer
    0.28
    Activations Density 0.013%

    No Known Activations