© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 22-TRANSCODER-HP
    7. 130903
    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
     rej
    -0.27
     divorced
    -0.26
    zÄĻ
    -0.26
    ä¹ŁåĽłæѤ
    -0.25
    uju
    -0.24
    ajÄħcy
    -0.24
     arc
    -0.24
    OLT
    -0.24
    CallCheck
    -0.23
    -bordered
    -0.23
    POSITIVE LOGITS
    [Index
    0.30
    èĬĤ
    0.27
    [parent
    0.26
    rique
    0.25
     Gü
    0.25
    ç¿»
    0.25
    [R
    0.24
    å¸Ŀ
    0.24
    ÅĦ
    0.24
    转
    0.24
    Activations Density 0.009%

    No Known Activations