© 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. 99023
    Prev
    Next
    INDEX
    Explanations

    technology/mixed content

    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
    EntityType
    -0.27
    çļĦæķ´ä½ĵ
    -0.26
    semblies
    -0.25
    .createFrom
    -0.24
    matic
    -0.24
    ç´§åĩij
    -0.24
     Lama
    -0.23
    .wrap
    -0.23
    intage
    -0.23
     dziaÅĤ
    -0.23
    POSITIVE LOGITS
     accompanying
    0.40
    éĻĦå±ŀ
    0.40
     accessory
    0.37
    éħįå¥Ĺ
    0.35
    ä¼´éļı
    0.34
    è¾ħ
    0.34
    è¾ħåĬ©
    0.33
     auxiliary
    0.32
     accessories
    0.32
    éħįå¥Ĺ设æĸ½
    0.32
    Activations Density 0.006%

    No Known Activations