© 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. 20-TRANSCODER-HP
    7. 142065
    Prev
    Next
    INDEX
    Explanations

    Grammatical sentences

    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
     environmentally
    -0.30
     environmental
    -0.29
    说åĩº
    -0.24
     thereafter
    -0.24
    æݥ触
    -0.24
    tra
    -0.24
    oth
    -0.24
     either
    -0.24
    rys
    -0.24
     whisper
    -0.24
    POSITIVE LOGITS
    chosen
    0.27
    æĢĴ
    0.27
    åħĪæĺ¯
    0.27
    åĢ¨
    0.26
    нÑİ
    0.26
    казан
    0.25
    è¹Ĭ
    0.25
    欲
    0.25
    istinguished
    0.25
    豪
    0.24
    Activations Density 10.557%

    No Known Activations