© 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. 98948
    Prev
    Next
    INDEX
    Explanations

    seed

    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
    ³³
    -0.28
     Âł
    -0.27
     Daughter
    -0.26
    undle
    -0.26
    ³³³³³³³
    -0.25
    ³³³
    -0.25
    å¤
    -0.25
    pta
    -0.24
     manifold
    -0.24
     could
    -0.23
    POSITIVE LOGITS
     Blvd
    0.29
    âĢ¦↵↵↵↵
    0.25
    ...↵↵↵↵
    0.24
     writers
    0.23
    lood
    0.22
     protestors
    0.22
    ?"↵↵↵↵
    0.22
    æĸĵ
    0.22
    ybrid
    0.22
    éĻį
    0.21
    Activations Density 0.001%

    No Known Activations