© 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. 130752
    Prev
    Next
    INDEX
    Explanations

    clicking online

    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
    è¿Ļ个æĹ¶ä»£
    -0.28
    istol
    -0.27
    åĨ»ç»ĵ
    -0.25
     ".";↵
    -0.24
    SELL
    -0.24
    ãĢĤ",↵
    -0.24
    è¿Ļ个ä¸ĸçķĮ
    -0.24
    ãģ¨ãģĦãģĨãĤĤãģ®
    -0.24
    aved
    -0.23
    .\"
    -0.23
    POSITIVE LOGITS
     correctly
    0.28
     slide
    0.28
    bh
    0.27
    standing
    0.27
     exc
    0.26
     notices
    0.26
     adm
    0.26
     h
    0.26
    s
    0.26
     multi
    0.25
    Activations Density 0.010%

    No Known Activations