© 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. 30-TRANSCODER-HP
    7. 96930
    Prev
    Next
    INDEX
    Explanations

    Expressing gratitude or positivity

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    éĿ¶
    -0.28
     propositions
    -0.27
     jud
    -0.26
    沫
    -0.26
     potatoes
    -0.26
    COPE
    -0.25
     Gors
    -0.25
     stret
    -0.25
    pez
    -0.25
    geom
    -0.25
    POSITIVE LOGITS
    ative
    0.31
     progress
    0.30
    Progress
    0.29
    æĦŁè°¢
    0.28
    _progress
    0.28
     Progress
    0.28
    itional
    0.28
    ATIVE
    0.27
    _PROGRESS
    0.27
    progress
    0.27
    Activations Density 0.886%

    No Known Activations