© 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. 97277
    Prev
    Next
    INDEX
    Explanations

    comparative adjectives

    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
    Negative Logits
    .xlim
    -0.26
    åįĪåIJİ
    -0.24
    æĬļåħ»
    -0.24
    奢
    -0.23
     Brow
    -0.23
    幸è¿IJ
    -0.23
    (padding
    -0.23
    ãģ®æĸ¹ãģĮ
    -0.23
    enh
    -0.23
    OLTIP
    -0.23
    POSITIVE LOGITS
    izin
    0.32
    oire
    0.31
    izr
    0.28
     yab
    0.27
    ilan
    0.27
     repr
    0.26
    è¯Ħä»·
    0.26
    izi
    0.26
     quantities
    0.25
    ias
    0.25
    Activations Density 0.015%

    No Known Activations