© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 22-TRANSCODER-HP
    7. 130771
    Prev
    Next
    INDEX
    Explanations

    Code and unstructured text

    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
     Âł
    -0.24
     Âł Âł
    -0.23
    'aff
    -0.22
    ped
    -0.22
     Âł Âł Âł Âł
    -0.19
    顧
    -0.19
    inous
    -0.18
     Dzi
    -0.18
    ."↵↵↵
    -0.18
    å£ĵ
    -0.18
    POSITIVE LOGITS
    åĪĨ享
    0.19
     main
    0.19
    .persist
    0.19
    份é¢Ŀ
    0.18
     Bowl
    0.18
     split
    0.18
    åľĪåŃIJ
    0.18
     li
    0.18
    }\.[
    0.18
     quits
    0.18
    Activations Density 0.349%

    No Known Activations