© 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. 112787
    Prev
    Next
    INDEX
    Explanations

    Imperative verbs

    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
    Not in Any Lists

    No Comments

    Negative Logits
    aco
    -0.33
    WARE
    -0.28
    year
    -0.25
    åĬ¨çī©
    -0.24
    average
    -0.24
    iss
    -0.24
    شت
    -0.23
     ones
    -0.23
    åįģä½Ļå¹´
    -0.23
     dwar
    -0.23
    POSITIVE LOGITS
    ushing
    0.27
    oscope
    0.26
    enze
    0.26
    ole
    0.26
    ãģ¤ãģ®
    0.25
    带æĿ¥çļĦ
    0.25
    adox
    0.24
    æīĢ带æĿ¥çļĦ
    0.24
    .Nodes
    0.24
    ousse
    0.24
    Activations Density 0.008%

    No Known Activations