© 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. 129579
    Prev
    Next
    INDEX
    Explanations

    Superlative/extreme quality

    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
    æľĢ容æĺĵ
    -0.29
    kel
    -0.29
    èĭ¦ç¬ij
    -0.28
    ç½ijå°ıç¼ĸ
    -0.26
     busiest
    -0.26
     happiest
    -0.26
     foremost
    -0.25
     ÑģамÑĭÑħ
    -0.25
     favourites
    -0.25
    第ä¸ĢåIJį
    -0.25
    POSITIVE LOGITS
    	Copyright
    0.29
    尽管
    0.28
     ment
    0.27
    UMENT
    0.26
    assed
    0.26
     entity
    0.26
    -msg
    0.25
    flammatory
    0.25
     pint
    0.24
     Ment
    0.24
    Activations Density 0.023%

    No Known Activations