© 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. 31-TRANSCODER-HP
    7. 17742
    Prev
    Next
    INDEX
    Explanations

    related to growth

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_31.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.31.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     disap
    -0.27
    contain
    -0.27
    Contain
    -0.27
     kitty
    -0.26
    .backward
    -0.26
    erp
    -0.26
    Descriptors
    -0.26
    åĵģå¾·
    -0.26
    ylv
    -0.25
     Posting
    -0.25
    POSITIVE LOGITS
    çĶŁéķ¿
    0.40
     grow
    0.39
     growing
    0.38
     inf
    0.36
     grows
    0.36
    æ¤į
    0.36
     growth
    0.34
     grown
    0.33
     cult
    0.32
    Grow
    0.32
    Activations Density 0.203%

    No Known Activations