© 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. 20-TRANSCODER-HP
    7. 140939
    Prev
    Next
    INDEX
    Explanations

    comparative adjectives/adverbs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     celebr
    -0.26
    oux
    -0.25
    åºĨç¥Ŀ
    -0.25
    羯
    -0.24
     alternate
    -0.24
    åĿļå®ļä¸į移
    -0.24
     Gest
    -0.23
    é¢ļ
    -0.23
    æ¼±
    -0.23
     postal
    -0.23
    POSITIVE LOGITS
     than
    0.33
    _than
    0.28
    -than
    0.28
    以å¾Ģ
    0.27
    ä¸įå¦Ĥ
    0.27
    /#
    0.26
     stripper
    0.25
    olor
    0.25
    Ļ¶
    0.24
     exhaust
    0.24
    Activations Density 60.413%

    No Known Activations