© 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. 129698
    Prev
    Next
    INDEX
    Explanations

    Names

    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
    éĿĻæĢģ
    -0.25
    ä½İä»·
    -0.25
     Essen
    -0.24
     indirect
    -0.24
    èĮ«çĦ¶
    -0.23
    .Persistence
    -0.23
    å¤ĸæĿ¥
    -0.23
     indirectly
    -0.23
    ney
    -0.23
     INDIRECT
    -0.23
    POSITIVE LOGITS
    isks
    0.26
     cites
    0.26
     formats
    0.25
     wings
    0.25
    åľ¨æѤä¹ĭåīį
    0.25
    à¹Ĥà¸ķ
    0.24
    toc
    0.24
     relevant
    0.24
     logic
    0.24
     growth
    0.24
    Activations Density 0.005%

    No Known Activations