© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 32-TRANSCODER-HP
    7. 41732
    Prev
    Next
    INDEX
    Explanations

    growth

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    éĥ¨
    -0.29
    compan
    -0.27
    ç²¾ç»Ĩ
    -0.26
     unle
    -0.26
    åħ¨ç¨ĭ
    -0.25
    íĭĢ
    -0.25
    eya
    -0.24
    ographies
    -0.24
    éĵ¾
    -0.24
    æŀ«
    -0.24
    POSITIVE LOGITS
     growth
    0.39
     grows
    0.34
     Growth
    0.34
     grown
    0.33
     growing
    0.32
     solid
    0.29
    growth
    0.29
    çĶŁéķ¿
    0.29
     grow
    0.28
     grew
    0.27
    Activations Density 0.009%

    No Known Activations