© 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. 88329
    Prev
    Next
    INDEX
    Explanations

    auxiliary verbs

    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
    anke
    -0.30
    解æŀIJ
    -0.26
    çĪ±ä¸Ĭ
    -0.26
    erce
    -0.25
    ä½ıåĿĢ
    -0.25
    ä½ķ
    -0.24
     resta
    -0.24
    offee
    -0.24
     xxxx
    -0.24
    Regressor
    -0.24
    POSITIVE LOGITS
     :↵↵↵↵
    0.25
     Ellen
    0.24
    å¿ĥåºķ
    0.24
    yled
    0.24
     arc
    0.24
    æĪIJé¾Ļ
    0.23
    æł¹æľ¬å°±ä¸į
    0.23
    mdat
    0.23
     Arc
    0.23
     Wrapped
    0.23
    Activations Density 0.009%

    No Known Activations